|
Records |
Links |
|
Author |
Damian Sojka; Yuyang Liu; Dipam Goswami; Sebastian Cygert; Bartłomiej Twardowski; Joost van de Weijer |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Technical Report for ICCV 2023 Visual Continual Learning Challenge: Continuous Test-time Adaptation for Semantic Segmentation |
Type |
Miscellaneous |
|
Year |
2023 |
Publication |
Arxiv |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract ![sorted by Abstract field, descending order (down)](img/sort_desc.gif) |
The goal of the challenge is to develop a test-time adaptation (TTA) method, which could adapt the model to gradually changing domains in video sequences for semantic segmentation task. It is based on a synthetic driving video dataset – SHIFT. The source model is trained on images taken during daytime in clear weather. Domain changes at test-time are mainly caused by varying weather conditions and times of day. The TTA methods are evaluated in each image sequence (video) separately, meaning the model is reset to the source model state before the next sequence. Images come one by one and a prediction has to be made at the arrival of each frame. Each sequence is composed of 401 images and starts with the source domain, then gradually drifts to a different one (changing weather or time of day) until the middle of the sequence. In the second half of the sequence, the domain gradually shifts back to the source one. Ground truth data is available only for the validation split of the SHIFT dataset, in which there are only six sequences that start and end with the source domain. We conduct an analysis specifically on those sequences. Ground truth data for test split, on which the developed TTA methods are evaluated for leader board ranking, are not publicly available.
The proposed solution secured a 3rd place in a challenge and received an innovation award. Contrary to the solutions that scored better, we did not use any external pretrained models or specialized data augmentations, to keep the solutions as general as possible. We have focused on analyzing the distributional shift and developing a method that could adapt to changing data dynamics and generalize across different scenarios. |
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
LAMP |
Approved |
no |
|
|
Call Number |
Admin @ si @ SLG2023 |
Serial |
3993 |
|
Permanent link to this record |
|
|
|
|
Author |
Souhail Bakkali; Sanket Biswas; Zuheng Ming; Mickael Coustaty; Marçal Rusiñol; Oriol Ramos Terrades; Josep Llados |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
TransferDoc: A Self-Supervised Transferable Document Representation Learning Model Unifying Vision and Language |
Type |
Miscellaneous |
|
Year |
2023 |
Publication |
Arxiv |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract ![sorted by Abstract field, descending order (down)](img/sort_desc.gif) |
The field of visual document understanding has witnessed a rapid growth in emerging challenges and powerful multi-modal strategies. However, they rely on an extensive amount of document data to learn their pretext objectives in a ``pre-train-then-fine-tune'' paradigm and thus, suffer a significant performance drop in real-world online industrial settings. One major reason is the over-reliance on OCR engines to extract local positional information within a document page. Therefore, this hinders the model's generalizability, flexibility and robustness due to the lack of capturing global information within a document image. We introduce TransferDoc, a cross-modal transformer-based architecture pre-trained in a self-supervised fashion using three novel pretext objectives. TransferDoc learns richer semantic concepts by unifying language and visual representations, which enables the production of more transferable models. Besides, two novel downstream tasks have been introduced for a ``closer-to-real'' industrial evaluation scenario where TransferDoc outperforms other state-of-the-art approaches. |
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
DAG |
Approved |
no |
|
|
Call Number |
Admin @ si @ BBM2023 |
Serial |
3995 |
|
Permanent link to this record |
|
|
|
|
Author |
Adarsh Tiwari; Sanket Biswas; Josep Llados |
![goto web page url](img/www.gif)
|
|
Title |
Can Pre-trained Language Models Help in Understanding Handwritten Symbols? |
Type |
Conference Article |
|
Year |
2023 |
Publication |
17th International Conference on Document Analysis and Recognition |
Abbreviated Journal |
|
|
|
Volume |
14193 |
Issue |
|
Pages |
199–211 |
|
|
Keywords |
|
|
|
Abstract ![sorted by Abstract field, descending order (down)](img/sort_desc.gif) |
The emergence of transformer models like BERT, GPT-2, GPT-3, RoBERTa, T5 for natural language understanding tasks has opened the floodgates towards solving a wide array of machine learning tasks in other modalities like images, audio, music, sketches and so on. These language models are domain-agnostic and as a result could be applied to 1-D sequences of any kind. However, the key challenge lies in bridging the modality gap so that they could generate strong features beneficial for out-of-domain tasks. This work focuses on leveraging the power of such pre-trained language models and discusses the challenges in predicting challenging handwritten symbols and alphabets. |
|
|
Address |
San Jose; CA; USA; August 2023 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICDAR |
|
|
Notes |
DAG |
Approved |
no |
|
|
Call Number |
Admin @ si @ TBL2023 |
Serial |
3908 |
|
Permanent link to this record |
|
|
|
|
Author |
Jose Luis Gomez |
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Synth-to-real semi-supervised learning for visual tasks |
Type |
Book Whole |
|
Year |
2023 |
Publication |
Going beyond Classification Problems for the Continual Learning of Deep Neural Networks |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract ![sorted by Abstract field, descending order (down)](img/sort_desc.gif) |
The curse of data labeling is a costly bottleneck in supervised deep learning, where large amounts of labeled data are needed to train intelligent systems. In onboard perception for autonomous driving, this cost corresponds to the labeling of raw data from sensors such as cameras, LiDARs, RADARs, etc. Therefore, synthetic data with automatically generated ground truth (labels) has aroused as a reliable alternative for training onboard perception models.
However, synthetic data commonly suffers from synth-to-real domain shift, i.e., models trained on the synthetic domain do not show their achievable accuracy when performing in the real world. This shift needs to be addressed by techniques falling in the realm of domain adaptation (DA).
The semi-supervised learning (SSL) paradigm can be followed to address DA. In this case, a model is trained using source data with labels (here synthetic) and leverages minimal knowledge from target data (here the real world) to generate pseudo-labels. These pseudo-labels help the training process to reduce the gap between the source and the target domains. In general, we can assume accessing both, pseudo-labels and a few amounts of human-provided labels for the target-domain data. However, the most interesting and challenging setting consists in assuming that we do not have human-provided labels at all. This setting is known as unsupervised domain adaptation (UDA). This PhD focuses on applying SSL to the UDA setting, for onboard visual tasks related to autonomous driving. We start by addressing the synth-to-real UDA problem on onboard vision-based object detection (pedestrians and cars), a critical task for autonomous driving and driving assistance. In particular, we propose to apply an SSL technique known as co-training, which we adapt to work with deep models that process a multi-modal input. The multi-modality consists of the visual appearance of the images (RGB) and their monocular depth estimation. The synthetic data we use as the source domain contains both, object bounding boxes and depth information. This prior knowledge is the
starting point for the co-training technique, which iteratively labels unlabeled real-world data and uses such pseudolabels (here bounding boxes with an assigned object class) to progressively improve the labeling results. Along this
process, two models collaborate to automatically label the images, in a way that one model compensates for the errors of the other, so avoiding error drift. While this automatic labeling process is done offline, the resulting pseudolabels can be used to train object detection models that must perform in real-time onboard a vehicle. We show that multi-modal co-training improves the labeling results compared to single-modal co-training, remaining competitive compared to human labeling.
Given the success of co-training in the context of object detection, we have also adapted this technique to a more crucial and challenging visual task, namely, onboard semantic segmentation. In fact, providing labels for a single image
can take from 30 to 90 minutes for a human labeler, depending on the content of the image. Thus, developing automatic labeling techniques for this visual task is of great interest to the automotive industry. In particular, the new co-training framework addresses synth-to-real UDA by an initial stage of self-training. Intermediate models arising from this stage are used to start the co-training procedure, for which we have elaborated an accurate collaboration policy between the two models performing the automatic labeling. Moreover, our co-training seamlessly leverages datasets from different synthetic domains. In addition, the co-training procedure is agnostic to the loss function used to train the semantic segmentation models which perform the automatic labeling. We achieve state-of-the-art results on publicly available benchmark datasets, again, remaining competitive compared to human labeling.
Finally, on the ground of our previous experience, we have designed and implemented a new SSL technique for UDA in the context of visual semantic segmentation. In this case, we mimic the labeling methodology followed by human labelers. In particular, rather than labeling full images at a time, categories of semantic classes are defined and only those are labeled in a labeling pass. In fact, different human labelers can become specialists in labeling different categories. Afterward, these per-category-labeled layers are combined to provide fully labeled images. Our technique is inspired by this methodology since we perform synth-to-real UDA per category, using the self-training stage previously developed as part of our co-training framework. The pseudo-labels obtained for each category are finally
fused to obtain fully automatically labeled images. In this context, we have also contributed to the development of a new photo-realistic synthetic dataset based on path-tracing rendering. Our new SSL technique seamlessly leverages publicly available synthetic datasets as well as this new one to obtain state-of-the-art results on synth-to-real UDA for semantic segmentation. We show that the new dataset allows us to reach better labeling accuracy than previously existing datasets, at the same time that it complements well them when combined. Moreover, we also show that the new human-inspired SSL technique outperforms co-training. |
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
Ph.D. thesis |
|
|
Publisher |
IMPRIMA |
Place of Publication |
|
Editor |
Antonio Lopez |
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
ADAS |
Approved |
no |
|
|
Call Number |
Admin @ si @ Gom2023 |
Serial |
3961 |
|
Permanent link to this record |
|
|
|
|
Author |
Mert Kilickaya; Joost van de Weijer; Yuki M. Asano |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Towards Label-Efficient Incremental Learning: A Survey |
Type |
Miscellaneous |
|
Year |
2023 |
Publication |
Arxiv |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract ![sorted by Abstract field, descending order (down)](img/sort_desc.gif) |
The current dominant paradigm when building a machine learning model is to iterate over a dataset over and over until convergence. Such an approach is non-incremental, as it assumes access to all images of all categories at once. However, for many applications, non-incremental learning is unrealistic. To that end, researchers study incremental learning, where a learner is required to adapt to an incoming stream of data with a varying distribution while preventing forgetting of past knowledge. Significant progress has been made, however, the vast majority of works focus on the fully supervised setting, making these algorithms label-hungry thus limiting their real-life deployment. To that end, in this paper, we make the first attempt to survey recently growing interest in label-efficient incremental learning. We identify three subdivisions, namely semi-, few-shot- and self-supervised learning to reduce labeling efforts. Finally, we identify novel directions that can further enhance label-efficiency and improve incremental learning scalability. Project website: this https URL. |
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
LAMP |
Approved |
no |
|
|
Call Number |
Admin @ si @ KWA2023 |
Serial |
3994 |
|
Permanent link to this record |
|
|
|
|
Author |
George Tom; Minesh Mathew; Sergi Garcia Bordils; Dimosthenis Karatzas; CV Jawahar |
![goto web page url](img/www.gif)
|
|
Title |
Reading Between the Lanes: Text VideoQA on the Road |
Type |
Conference Article |
|
Year |
2023 |
Publication |
17th International Conference on Document Analysis and Recognition |
Abbreviated Journal |
|
|
|
Volume |
14192 |
Issue |
|
Pages |
137–154 |
|
|
Keywords |
VideoQA; scene text; driving videos |
|
|
Abstract ![sorted by Abstract field, descending order (down)](img/sort_desc.gif) |
Text and signs around roads provide crucial information for drivers, vital for safe navigation and situational awareness. Scene text recognition in motion is a challenging problem, while textual cues typically appear for a short time span, and early detection at a distance is necessary. Systems that exploit such information to assist the driver should not only extract and incorporate visual and textual cues from the video stream but also reason over time. To address this issue, we introduce RoadTextVQA, a new dataset for the task of video question answering (VideoQA) in the context of driver assistance. RoadTextVQA consists of 3, 222 driving videos collected from multiple countries, annotated with 10, 500 questions, all based on text or road signs present in the driving videos. We assess the performance of state-of-the-art video question answering models on our RoadTextVQA dataset, highlighting the significant potential for improvement in this domain and the usefulness of the dataset in advancing research on in-vehicle support systems and text-aware multimodal question answering. The dataset is available at http://cvit.iiit.ac.in/research/projects/cvit-projects/roadtextvqa. |
|
|
Address |
San Jose; CA; USA; August 2023 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICDAR |
|
|
Notes |
DAG |
Approved |
no |
|
|
Call Number |
Admin @ si @ TMG2023 |
Serial |
3906 |
|
Permanent link to this record |
|
|
|
|
Author |
Damian Sojka; Sebastian Cygert; Bartlomiej Twardowski; Tomasz Trzcinski |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptation |
Type |
Conference Article |
|
Year |
2023 |
Publication |
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
3491-3495 |
|
|
Keywords |
|
|
|
Abstract ![sorted by Abstract field, descending order (down)](img/sort_desc.gif) |
Test-time adaptation is a promising research direction that allows the source model to adapt itself to changes in data distribution without any supervision. Yet, current methods are usually evaluated on benchmarks that are only a simplification of real-world scenarios. Hence, we propose to validate test-time adaptation methods using the recently introduced datasets for autonomous driving, namely CLAD-C and SHIFT. We observe that current test-time adaptation methods struggle to effectively handle varying degrees of domain shift, often resulting in degraded performance that falls below that of the source model. We noticed that the root of the problem lies in the inability to preserve the knowledge of the source model and adapt to dynamically changing, temporally correlated data streams. Therefore, we enhance well-established self-training framework by incorporating a small memory buffer to increase model stability and at the same time perform dynamic adaptation based on the intensity of domain shift. The proposed method, named AR-TTA, outperforms existing approaches on both synthetic and more real-world benchmarks and shows robustness across a variety of TTA scenarios. |
|
|
Address |
Paris; France; October 2023 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICCVW |
|
|
Notes |
LAMP |
Approved |
no |
|
|
Call Number |
Admin @ si @ SCT2023 |
Serial |
3943 |
|
Permanent link to this record |
|
|
|
|
Author |
David Pujol Perich; Albert Clapes; Sergio Escalera |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
SADA: Semantic adversarial unsupervised domain adaptation for Temporal Action Localization |
Type |
Miscellaneous |
|
Year |
2023 |
Publication |
Arxiv |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract ![sorted by Abstract field, descending order (down)](img/sort_desc.gif) |
Temporal Action Localization (TAL) is a complex task that poses relevant challenges, particularly when attempting to generalize on new -- unseen -- domains in real-world applications. These scenarios, despite realistic, are often neglected in the literature, exposing these solutions to important performance degradation. In this work, we tackle this issue by introducing, for the first time, an approach for Unsupervised Domain Adaptation (UDA) in sparse TAL, which we refer to as Semantic Adversarial unsupervised Domain Adaptation (SADA). Our contributions are threefold: (1) we pioneer the development of a domain adaptation model that operates on realistic sparse action detection benchmarks; (2) we tackle the limitations of global-distribution alignment techniques by introducing a novel adversarial loss that is sensitive to local class distributions, ensuring finer-grained adaptation; and (3) we present a novel set of benchmarks based on EpicKitchens100 and CharadesEgo, that evaluate multiple domain shifts in a comprehensive manner. Our experiments indicate that SADA improves the adaptation across domains when compared to fully supervised state-of-the-art and alternative UDA methods, attaining a performance boost of up to 6.14% mAP. |
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
HUPBA |
Approved |
no |
|
|
Call Number |
Admin @ si @ PCE2023 |
Serial |
4014 |
|
Permanent link to this record |
|
|
|
|
Author |
Wenwen Yu; Chengquan Zhang; Haoyu Cao; Wei Hua; Bohan Li; Huang Chen; Mingyu Liu; Mingrui Chen; Jianfeng Kuang; Mengjun Cheng; Yuning Du; Shikun Feng; Xiaoguang Hu; Pengyuan Lyu; Kun Yao; Yuechen Yu; Yuliang Liu; Wanxiang Che; Errui Ding; Cheng-Lin Liu; Jiebo Luo; Shuicheng Yan; Min Zhang; Dimosthenis Karatzas; Xing Sun; Jingdong Wang; Xiang Bai |
![goto web page url](img/www.gif)
|
|
Title |
ICDAR 2023 Competition on Structured Text Extraction from Visually-Rich Document Images |
Type |
Conference Article |
|
Year |
2023 |
Publication |
17th International Conference on Document Analysis and Recognition |
Abbreviated Journal |
|
|
|
Volume |
14188 |
Issue |
|
Pages |
536–552 |
|
|
Keywords |
|
|
|
Abstract ![sorted by Abstract field, descending order (down)](img/sort_desc.gif) |
Structured text extraction is one of the most valuable and challenging application directions in the field of Document AI. However, the scenarios of past benchmarks are limited, and the corresponding evaluation protocols usually focus on the submodules of the structured text extraction scheme. In order to eliminate these problems, we organized the ICDAR 2023 competition on Structured text extraction from Visually-Rich Document images (SVRD). We set up two tracks for SVRD including Track 1: HUST-CELL and Track 2: Baidu-FEST, where HUST-CELL aims to evaluate the end-to-end performance of Complex Entity Linking and Labeling, and Baidu-FEST focuses on evaluating the performance and generalization of Zero-shot/Few-shot Structured Text extraction from an end-to-end perspective. Compared to the current document benchmarks, our two tracks of competition benchmark enriches the scenarios greatly and contains more than 50 types of visually-rich document images (mainly from the actual enterprise applications). The competition opened on 30th December, 2022 and closed on 24th March, 2023. There are 35 participants and 91 valid submissions received for Track 1, and 15 participants and 26 valid submissions received for Track 2. In this report we will presents the motivation, competition datasets, task definition, evaluation protocol, and submission summaries. According to the performance of the submissions, we believe there is still a large gap on the expected information extraction performance for complex and zero-shot scenarios. It is hoped that this competition will attract many researchers in the field of CV and NLP, and bring some new thoughts to the field of Document AI. |
|
|
Address |
San Jose; CA; USA; August 2023 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICDAR |
|
|
Notes |
DAG |
Approved |
no |
|
|
Call Number |
Admin @ si @ YZC2023 |
Serial |
3896 |
|
Permanent link to this record |
|
|
|
|
Author |
German Barquero; Sergio Escalera; Cristina Palmero |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction |
Type |
Conference Article |
|
Year |
2023 |
Publication |
IEEE/CVF International Conference on Computer Vision (ICCV) Workshops |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
2317-2327 |
|
|
Keywords |
|
|
|
Abstract ![sorted by Abstract field, descending order (down)](img/sort_desc.gif) |
Stochastic human motion prediction (HMP) has generally been tackled with generative adversarial networks and variational autoencoders. Most prior works aim at predicting highly diverse movements in terms of the skeleton joints’ dispersion. This has led to methods predicting fast and motion-divergent movements, which are often unrealistic and incoherent with past motion. Such methods also neglect contexts that need to anticipate diverse low-range behaviors, or actions, with subtle joint displacements. To address these issues, we present BeLFusion, a model that, for the first time, leverages latent diffusion models in HMP to sample from a latent space where behavior is disentangled from pose and motion. As a result, diversity is encouraged from a behavioral perspective. Thanks to our behavior
coupler’s ability to transfer sampled behavior to ongoing motion, BeLFusion’s predictions display a variety of behaviors that are significantly more realistic than the state of the art. To support it, we introduce two metrics, the Area of
the Cumulative Motion Distribution, and the Average Pairwise Distance Error, which are correlated to our definition of realism according to a qualitative study with 126 participants. Finally, we prove BeLFusion’s generalization power in a new cross-dataset scenario for stochastic HMP. |
|
|
Address |
2-6 October 2023. Paris (France) |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICCV |
|
|
Notes |
HUPBA; no menciona |
Approved |
no |
|
|
Call Number |
Admin @ si @ BEP2023 |
Serial |
3829 |
|
Permanent link to this record |
|
|
|
|
Author |
Lei Kang; Lichao Zhang; Dazhi Jiang |
![goto web page url](img/www.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Learning Robust Self-Attention Features for Speech Emotion Recognition with Label-Adaptive Mixup |
Type |
Conference Article |
|
Year |
2023 |
Publication |
IEEE International Conference on Acoustics, Speech and Signal Processing |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract ![sorted by Abstract field, descending order (down)](img/sort_desc.gif) |
Speech Emotion Recognition (SER) is to recognize human emotions in a natural verbal interaction scenario with machines, which is considered as a challenging problem due to the ambiguous human emotions. Despite the recent progress in SER, state-of-the-art models struggle to achieve a satisfactory performance. We propose a self-attention based method with combined use of label-adaptive mixup and center loss. By adapting label probabilities in mixup and fitting center loss to the mixup training scheme, our proposed method achieves a superior performance to the state-of-the-art methods. |
|
|
Address |
Rodhes Islands; Greece; June 2023 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICASSP |
|
|
Notes |
LAMP |
Approved |
no |
|
|
Call Number |
Admin @ si @ KZJ2023 |
Serial |
3984 |
|
Permanent link to this record |
|
|
|
|
Author |
Qingshan Chen; Zhenzhen Quan; Yifan Hu; Yujun Li; Zhi Liu; Mikhail Mozerov |
![goto web page url](img/www.gif)
|
|
Title |
MSIF: multi-spectrum image fusion method for cross-modality person re-identification |
Type |
Journal Article |
|
Year |
2023 |
Publication |
International Journal of Machine Learning and Cybernetics |
Abbreviated Journal |
IJMLC |
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract ![sorted by Abstract field, descending order (down)](img/sort_desc.gif) |
Sketch-RGB cross-modality person re-identification (ReID) is a challenging task that aims to match a sketch portrait drawn by a professional artist with a full-body photo taken by surveillance equipment to deal with situations where the monitoring equipment is damaged at the accident scene. However, sketch portraits only provide highly abstract frontal body contour information and lack other important features such as color, pose, behavior, etc. The difference in saliency between the two modalities brings new challenges to cross-modality person ReID. To overcome this problem, this paper proposes a novel dual-stream model for cross-modality person ReID, which is able to mine modality-invariant features to reduce the discrepancy between sketch and camera images end-to-end. More specifically, we propose a multi-spectrum image fusion (MSIF) method, which aims to exploit the image appearance changes brought by multiple spectrums and guide the network to mine modality-invariant commonalities during training. It only processes the spectrum of the input images without adding additional calculations and model complexity, which can be easily integrated into other models. Moreover, we introduce a joint structure via a generalized mean pooling (GMP) layer and a self-attention (SA) mechanism to balance background and texture information and obtain the regional features with a large amount of information in the image. To further shrink the intra-class distance, a weighted regularized triplet (WRT) loss is developed without introducing additional hyperparameters. The model was first evaluated on the PKU Sketch ReID dataset, and extensive experimental results show that the Rank-1/mAP accuracy of our method is 87.00%/91.12%, reaching the current state-of-the-art performance. To further validate the effectiveness of our approach in handling cross-modality person ReID, we conducted experiments on two commonly used IR-RGB datasets (SYSU-MM01 and RegDB). The obtained results show that our method achieves competitive performance. These results confirm the ability of our method to effectively process images from different modalities. |
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
LAMP |
Approved |
no |
|
|
Call Number |
Admin @ si @ CQH2023 |
Serial |
3885 |
|
Permanent link to this record |
|
|
|
|
Author |
Joakim Bruslund Haurum; Sergio Escalera; Graham W. Taylor; Thomas B. |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Which Tokens to Use? Investigating Token Reduction in Vision Transformers |
Type |
Conference Article |
|
Year |
2023 |
Publication |
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract ![sorted by Abstract field, descending order (down)](img/sort_desc.gif) |
Since the introduction of the Vision Transformer (ViT), researchers have sought to make ViTs more efficient by removing redundant information in the processed tokens. While different methods have been explored to achieve this goal, we still lack understanding of the resulting reduction patterns and how those patterns differ across token reduction methods and datasets. To close this gap, we set out to understand the reduction patterns of 10 different token reduction methods using four image classification datasets. By systematically comparing these methods on the different classification tasks, we find that the Top-K pruning method is a surprisingly strong baseline. Through in-depth analysis of the different methods, we determine that: the reduction patterns are generally not consistent when varying the capacity of the backbone model, the reduction patterns of pruning-based methods significantly differ from fixed radial patterns, and the reduction patterns of pruning-based methods are correlated across classification datasets. Finally we report that the similarity of reduction patterns is a moderate-to-strong proxy for model performance. Project page at https://vap.aau.dk/tokens. |
|
|
Address |
Paris; France; October 2023 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICCVW |
|
|
Notes |
HUPBA |
Approved |
no |
|
|
Call Number |
Admin @ si @ BET2023 |
Serial |
3940 |
|
Permanent link to this record |
|
|
|
|
Author |
Benjia Zhou; Zhigang Chen; Albert Clapes; Jun Wan; Yanyan Liang; Sergio Escalera; Zhen Lei; Du Zhang |
![download PDF file pdf](img/file_PDF.gif)
![goto web page (via DOI) doi](img/doi.gif)
|
|
Title |
Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining |
Type |
Conference Article |
|
Year |
2023 |
Publication |
IEEE/CVF International Conference on Computer Vision (ICCV) Workshops |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract ![sorted by Abstract field, descending order (down)](img/sort_desc.gif) |
Sign Language Translation (SLT) is a challenging task due to its cross-domain nature, involving the translation of visual-gestural language to text. Many previous methods employ an intermediate representation, i.e., gloss sequences, to facilitate SLT, thus transforming it into a two-stage task of sign language recognition (SLR) followed by sign language translation (SLT). However, the scarcity of gloss-annotated sign language data, combined with the information bottleneck in the mid-level gloss representation, has hindered the further development of the SLT task. To address this challenge, we propose a novel Gloss-Free SLT based on Visual-Language Pretraining (GFSLT-VLP), which improves SLT by inheriting language-oriented prior knowledge from pre-trained models, without any gloss annotation assistance. Our approach involves two stages: (i) integrating Contrastive Language-Image Pre-training (CLIP) with masked self-supervised learning to create pre-tasks that bridge the semantic gap between visual and textual representations and restore masked sentences, and (ii) constructing an end-to-end architecture with an encoder-decoder-like structure that inherits the parameters of the pre-trained Visual Encoder and Text Decoder from the first stage. The seamless combination of these novel designs forms a robust sign language representation and significantly improves gloss-free sign language translation. In particular, we have achieved unprecedented improvements in terms of BLEU-4 score on the PHOENIX14T dataset (>+5) and the CSL-Daily dataset (>+3) compared to state-of-the-art gloss-free SLT methods. Furthermore, our approach also achieves competitive results on the PHOENIX14T dataset when compared with most of the gloss-based methods. |
|
|
Address |
Vancouver; Canada; June 2023 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICCVW |
|
|
Notes |
HUPBA; |
Approved |
no |
|
|
Call Number |
Admin @ si @ ZCC2023 |
Serial |
3839 |
|
Permanent link to this record |
|
|
|
|
Author |
Simone Zini; Alex Gomez-Villa; Marco Buzzelli; Bartlomiej Twardowski; Andrew D. Bagdanov; Joost Van de Weijer |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Planckian Jitter: countering the color-crippling effects of color jitter on self-supervised training |
Type |
Conference Article |
|
Year |
2023 |
Publication |
11th International Conference on Learning Representations |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract ![sorted by Abstract field, descending order (down)](img/sort_desc.gif) |
Several recent works on self-supervised learning are trained by mapping different augmentations of the same image to the same feature representation. The data augmentations used are of crucial importance to the quality of learned feature representations. In this paper, we analyze how the color jitter traditionally used in data augmentation negatively impacts the quality of the color features in learned feature representations. To address this problem, we propose a more realistic, physics-based color data augmentation – which we call Planckian Jitter – that creates realistic variations in chromaticity and produces a model robust to illumination changes that can be commonly observed in real life, while maintaining the ability to discriminate image content based on color information. Experiments confirm that such a representation is complementary to the representations learned with the currently-used color jitter augmentation and that a simple concatenation leads to significant performance gains on a wide range of downstream datasets. In addition, we present a color sensitivity analysis that documents the impact of different training methods on model neurons and shows that the performance of the learned features is robust with respect to illuminant variations. |
|
|
Address |
1 -5 May 2023, Kigali, Ruanda |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICLR |
|
|
Notes |
LAMP; 600.147; 611.008; 5300006 |
Approved |
no |
|
|
Call Number |
Admin @ si @ ZGB2023 |
Serial |
3820 |
|
Permanent link to this record |