|
Records |
Links |
|
Author |
Anjan Dutta; Zeynep Akata |
![download PDF file pdf](img/file_PDF.gif)
![goto web page (via DOI) doi](img/doi.gif)
|
|
Title |
Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval |
Type |
Conference Article |
|
Year |
2019 |
Publication |
32nd IEEE Conference on Computer Vision and Pattern Recognition |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
5089-5098 |
|
|
Keywords ![sorted by Keywords field, ascending order (up)](img/sort_asc.gif) |
|
|
|
Abstract |
Zero-shot sketch-based image retrieval (SBIR) is an emerging task in computer vision, allowing to retrieve natural images relevant to sketch queries that might not been seen in the training phase. Existing works either require aligned sketch-image pairs or inefficient memory fusion layer for mapping the visual information to a semantic space. In this work, we propose a semantically aligned paired cycle-consistent generative (SEM-PCYC) model for zero-shot SBIR, where each branch maps the visual information to a common semantic space via an adversarial training. Each of these branches maintains a cycle consistency that only requires supervision at category levels, and avoids the need of highly-priced aligned sketch-image pairs. A classification criteria on the generators' outputs ensures the visual to semantic space mapping to be discriminating. Furthermore, we propose to combine textual and hierarchical side information via a feature selection auto-encoder that selects discriminating side information within a same end-to-end model. Our results demonstrate a significant boost in zero-shot SBIR performance over the state-of-the-art on the challenging Sketchy and TU-Berlin datasets. |
|
|
Address |
Long beach; California; USA; June 2019 |
|
|
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 |
CVPR |
|
|
Notes |
DAG; 600.141; 600.121 |
Approved |
no |
|
|
Call Number |
Admin @ si @ DuA2019 |
Serial |
3268 |
|
Permanent link to this record |
|
|
|
|
Author |
Lu Yu; Vacit Oguz Yazici; Xialei Liu; Joost Van de Weijer; Yongmei Cheng; Arnau Ramisa |
![download PDF file pdf](img/file_PDF.gif)
![goto web page (via DOI) doi](img/doi.gif)
|
|
Title |
Learning Metrics from Teachers: Compact Networks for Image Embedding |
Type |
Conference Article |
|
Year |
2019 |
Publication |
32nd IEEE Conference on Computer Vision and Pattern Recognition |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
2907-2916 |
|
|
Keywords ![sorted by Keywords field, ascending order (up)](img/sort_asc.gif) |
|
|
|
Abstract |
Metric learning networks are used to compute image embeddings, which are widely used in many applications such as image retrieval and face recognition. In this paper, we propose to use network distillation to efficiently compute image embeddings with small networks. Network distillation has been successfully applied to improve image classification, but has hardly been explored for metric learning. To do so, we propose two new loss functions that model the
communication of a deep teacher network to a small student network. We evaluate our system in several datasets, including CUB-200-2011, Cars-196, Stanford Online Products and show that embeddings computed using small student networks perform significantly better than those computed using standard networks of similar size. Results on a very compact network (MobileNet-0.25), which can be
used on mobile devices, show that the proposed method can greatly improve Recall@1 results from 27.5% to 44.6%. Furthermore, we investigate various aspects of distillation for embeddings, including hint and attention layers, semisupervised learning and cross quality distillation. |
|
|
Address |
Long beach; California; june 2019 |
|
|
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 |
CVPR |
|
|
Notes |
LAMP; 600.109; 600.120 |
Approved |
no |
|
|
Call Number |
Admin @ si @ YYL2019 |
Serial |
3281 |
|
Permanent link to this record |
|
|
|
|
Author |
Ali Furkan Biten; Lluis Gomez; Marçal Rusiñol; Dimosthenis Karatzas |
![download PDF file pdf](img/file_PDF.gif)
![goto web page (via DOI) doi](img/doi.gif)
|
|
Title |
Good News, Everyone! Context driven entity-aware captioning for news images |
Type |
Conference Article |
|
Year |
2019 |
Publication |
32nd IEEE Conference on Computer Vision and Pattern Recognition |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
12458-12467 |
|
|
Keywords ![sorted by Keywords field, ascending order (up)](img/sort_asc.gif) |
|
|
|
Abstract |
Current image captioning systems perform at a merely descriptive level, essentially enumerating the objects in the scene and their relations. Humans, on the contrary, interpret images by integrating several sources of prior knowledge of the world. In this work, we aim to take a step closer to producing captions that offer a plausible interpretation of the scene, by integrating such contextual information into the captioning pipeline. For this we focus on the captioning of images used to illustrate news articles. We propose a novel captioning method that is able to leverage contextual information provided by the text of news articles associated with an image. Our model is able to selectively draw information from the article guided by visual cues, and to dynamically extend the output dictionary to out-of-vocabulary named entities that appear in the context source. Furthermore we introduce“ GoodNews”, the largest news image captioning dataset in the literature and demonstrate state-of-the-art results. |
|
|
Address |
Long beach; California; USA; june 2019 |
|
|
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 |
CVPR |
|
|
Notes |
DAG; 600.129; 600.135; 601.338; 600.121 |
Approved |
no |
|
|
Call Number |
Admin @ si @ BGR2019 |
Serial |
3289 |
|
Permanent link to this record |
|
|
|
|
Author |
Shifeng Zhang; Xiaobo Wang; Ajian Liu; Chenxu Zhao; Jun Wan; Sergio Escalera; Hailin Shi; Zezheng Wang; Stan Z. Li |
![download PDF file pdf](img/file_PDF.gif)
![goto web page (via DOI) doi](img/doi.gif)
|
|
Title |
A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofing |
Type |
Conference Article |
|
Year |
2019 |
Publication |
32nd IEEE Conference on Computer Vision and Pattern Recognition |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
919-928 |
|
|
Keywords ![sorted by Keywords field, ascending order (up)](img/sort_asc.gif) |
|
|
|
Abstract |
Face anti-spoofing is essential to prevent face recognition systems from a security breach. Much of the progresses have been made by the availability of face anti-spoofing benchmark datasets in recent years. However, existing face anti-spoofing benchmarks have limited number of subjects (≤170) and modalities (≤2), which hinder the further development of the academic community. To facilitate face anti-spoofing research, we introduce a large-scale multi-modal dataset, namely CASIA-SURF, which is the largest publicly available dataset for face anti-spoofing in terms of both subjects and visual modalities. Specifically, it consists of 1,000 subjects with 21,000 videos and each sample has 3 modalities (i.e., RGB, Depth and IR). We also provide a measurement set, evaluation protocol and training/validation/testing subsets, developing a new benchmark for face anti-spoofing. Moreover, we present a new multi-modal fusion method as baseline, which performs feature re-weighting to select the more informative channel features while suppressing the less useful ones for each modal. Extensive experiments have been conducted on the proposed dataset to verify its significance and generalization capability. The dataset is available at https://sites.google.com/qq.com/chalearnfacespoofingattackdete/. |
|
|
Address |
California; June 2019 |
|
|
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 |
CVPR |
|
|
Notes |
HuPBA; no proj |
Approved |
no |
|
|
Call Number |
Admin @ si @ ZWL2019 |
Serial |
3331 |
|
Permanent link to this record |
|
|
|
|
Author |
Ciprian Corneanu; Meysam Madadi; Sergio Escalera; Aleix M. Martinez |
![download PDF file pdf](img/file_PDF.gif)
![goto web page (via DOI) doi](img/doi.gif)
|
|
Title |
What does it mean to learn in deep networks? And, how does one detect adversarial attacks? |
Type |
Conference Article |
|
Year |
2019 |
Publication |
32nd IEEE Conference on Computer Vision and Pattern Recognition |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
4752-4761 |
|
|
Keywords ![sorted by Keywords field, ascending order (up)](img/sort_asc.gif) |
|
|
|
Abstract |
The flexibility and high-accuracy of Deep Neural Networks (DNNs) has transformed computer vision. But, the fact that we do not know when a specific DNN will work and when it will fail has resulted in a lack of trust. A clear example is self-driving cars; people are uncomfortable sitting in a car driven by algorithms that may fail under some unknown, unpredictable conditions. Interpretability and explainability approaches attempt to address this by uncovering what a DNN models, i.e., what each node (cell) in the network represents and what images are most likely to activate it. This can be used to generate, for example, adversarial attacks. But these approaches do not generally allow us to determine where a DNN will succeed or fail and why. i.e., does this learned representation generalize to unseen samples? Here, we derive a novel approach to define what it means to learn in deep networks, and how to use this knowledge to detect adversarial attacks. We show how this defines the ability of a network to generalize to unseen testing samples and, most importantly, why this is the case. |
|
|
Address |
California; June 2019 |
|
|
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 |
CVPR |
|
|
Notes |
HuPBA; no proj |
Approved |
no |
|
|
Call Number |
Admin @ si @ CME2019 |
Serial |
3332 |
|
Permanent link to this record |
|
|
|
|
Author |
Swathikiran Sudhakaran; Sergio Escalera; Oswald Lanz |
![download PDF file pdf](img/file_PDF.gif)
![goto web page (via DOI) doi](img/doi.gif)
|
|
Title |
LSTA: Long Short-Term Attention for Egocentric Action Recognition |
Type |
Conference Article |
|
Year |
2019 |
Publication |
32nd IEEE Conference on Computer Vision and Pattern Recognition |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
9946-9955 |
|
|
Keywords ![sorted by Keywords field, ascending order (up)](img/sort_asc.gif) |
|
|
|
Abstract |
Egocentric activity recognition is one of the most challenging tasks in video analysis. It requires a fine-grained discrimination of small objects and their manipulation. While some methods base on strong supervision and attention mechanisms, they are either annotation consuming or do not take spatio-temporal patterns into account. In this paper we propose LSTA as a mechanism to focus on features from spatial relevant parts while attention is being tracked smoothly across the video sequence. We demonstrate the effectiveness of LSTA on egocentric activity recognition with an end-to-end trainable two-stream architecture, achieving state-of-the-art performance on four standard benchmarks. |
|
|
Address |
California; June 2019 |
|
|
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 |
CVPR |
|
|
Notes |
HuPBA; no proj |
Approved |
no |
|
|
Call Number |
Admin @ si @ SEL2019 |
Serial |
3333 |
|
Permanent link to this record |