| |
Records |
Links |
|
Author |
Swathikiran Sudhakaran; Sergio Escalera;Oswald Lanz |
|
| |
Title |
Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries |
Type |
Journal Article |
| |
Year |
2021 |
Publication |
IEEE Transactions on Pattern Analysis and Machine Intelligence |
Abbreviated Journal |
TPAMI |
|
| |
Volume |
|
Issue |
|
Pages |
|
|
| |
Keywords |
|
|
| |
Abstract |
We present EgoACO, a deep neural architecture for video action recognition that learns to pool action-context-object descriptors from frame level features by leveraging the verb-noun structure of action labels in egocentric video datasets. The core component of EgoACO is class activation pooling (CAP), a differentiable pooling operation that combines ideas from bilinear pooling for fine-grained recognition and from feature learning for discriminative localization. CAP uses self-attention with a dictionary of learnable weights to pool from the most relevant feature regions. Through CAP, EgoACO learns to decode object and scene context descriptors from video frame features. For temporal modeling in EgoACO, we design a recurrent version of class activation pooling termed Long Short-Term Attention (LSTA). LSTA extends convolutional gated LSTM with built-in spatial attention and a re-designed output gate. Action, object and context descriptors are fused by a multi-head prediction that accounts for the inter-dependencies between noun-verb-action structured labels in egocentric video datasets. EgoACO features built-in visual explanations, helping learning and interpretation. Results on the two largest egocentric action recognition datasets currently available, EPIC-KITCHENS and EGTEA, show that by explicitly decoding action-context-object descriptors, EgoACO achieves state-of-the-art recognition performance. |
|
| |
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; no proj;MILAB |
Approved |
no |
|
| |
Call Number  |
Admin @ si @ SEL2021 |
Serial |
3656 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Swathikiran Sudhakaran; Sergio Escalera; Oswald Lanz |
|
| |
Title |
Gate-Shift-Fuse for Video Action Recognition |
Type |
Journal Article |
| |
Year |
2023 |
Publication |
IEEE Transactions on Pattern Analysis and Machine Intelligence |
Abbreviated Journal |
TPAMI |
|
| |
Volume |
45 |
Issue |
9 |
Pages |
10913-10928 |
|
| |
Keywords |
Action Recognition; Video Classification; Spatial Gating; Channel Fusion |
|
| |
Abstract |
Convolutional Neural Networks are the de facto models for image recognition. However 3D CNNs, the straight forward extension of 2D CNNs for video recognition, have not achieved the same success on standard action recognition benchmarks. One of the main reasons for this reduced performance of 3D CNNs is the increased computational complexity requiring large scale annotated datasets to train them in scale. 3D kernel factorization approaches have been proposed to reduce the complexity of 3D CNNs. Existing kernel factorization approaches follow hand-designed and hard-wired techniques. In this paper we propose Gate-Shift-Fuse (GSF), a novel spatio-temporal feature extraction module which controls interactions in spatio-temporal decomposition and learns to adaptively route features through time and combine them in a data dependent manner. GSF leverages grouped spatial gating to decompose input tensor and channel weighting to fuse the decomposed tensors. GSF can be inserted into existing 2D CNNs to convert them into an efficient and high performing spatio-temporal feature extractor, with negligible parameter and compute overhead. We perform an extensive analysis of GSF using two popular 2D CNN families and achieve state-of-the-art or competitive performance on five standard action recognition benchmarks. |
|
| |
Address |
1 Sept. 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 |
|
|
| |
Notes |
HUPBA; no menciona;MILAB |
Approved |
no |
|
| |
Call Number |
Admin @ si @ SEL2023 |
Serial |
3814 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Frederic Sampedro; Sergio Escalera; Anna Puig |
|
| |
Title |
Iterative Multiclass Multiscale Stacked Sequential Learning: definition and application to medical volume segmentation |
Type |
Journal Article |
| |
Year |
2014 |
Publication |
Pattern Recognition Letters |
Abbreviated Journal |
PRL |
|
| |
Volume |
46 |
Issue |
|
Pages |
1-10 |
|
| |
Keywords |
Machine learning; Sequential learning; Multi-class problems; Contextual learning; Medical volume segmentation |
|
| |
Abstract |
In this work we present the iterative multi-class multi-scale stacked sequential learning framework (IMMSSL), a novel learning scheme that is particularly suited for medical volume segmentation applications. This model exploits the inherent voxel contextual information of the structures of interest in order to improve its segmentation performance results. Without any feature set or learning algorithm prior assumption, the proposed scheme directly seeks to learn the contextual properties of a region from the predicted classifications of previous classifiers within an iterative scheme. Performance results regarding segmentation accuracy in three two-class and multi-class medical volume datasets show a significant improvement with respect to state of the art alternatives. Due to its easiness of implementation and its independence of feature space and learning algorithm, the presented machine learning framework could be taken into consideration as a first choice in complex volume segmentation 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 |
HuPBA;MILAB |
Approved |
no |
|
| |
Call Number |
Admin @ si @ SEP2014 |
Serial |
2550 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Javier Selva; Anders S. Johansen; Sergio Escalera; Kamal Nasrollahi; Thomas B. Moeslund; Albert Clapes |
|
| |
Title |
Video transformers: A survey |
Type |
Journal Article |
| |
Year |
2023 |
Publication |
IEEE Transactions on Pattern Analysis and Machine Intelligence |
Abbreviated Journal |
TPAMI |
|
| |
Volume |
45 |
Issue |
11 |
Pages |
12922-12943 |
|
| |
Keywords |
Artificial Intelligence; Computer Vision; Self-Attention; Transformers; Video Representations |
|
| |
Abstract |
Transformer models have shown great success handling long-range interactions, making them a promising tool for modeling video. However, they lack inductive biases and scale quadratically with input length. These limitations are further exacerbated when dealing with the high dimensionality introduced by the temporal dimension. While there are surveys analyzing the advances of Transformers for vision, none focus on an in-depth analysis of video-specific designs. In this survey, we analyze the main contributions and trends of works leveraging Transformers to model video. Specifically, we delve into how videos are handled at the input level first. Then, we study the architectural changes made to deal with video more efficiently, reduce redundancy, re-introduce useful inductive biases, and capture long-term temporal dynamics. In addition, we provide an overview of different training regimes and explore effective self-supervised learning strategies for video. Finally, we conduct a performance comparison on the most common benchmark for Video Transformers (i.e., action classification), finding them to outperform 3D ConvNets even with less computational complexity. |
|
| |
Address |
1 Nov. 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 |
|
|
| |
Notes |
HUPBA; no menciona;MILAB |
Approved |
no |
|
| |
Call Number |
Admin @ si @ SJE2023 |
Serial |
3823 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Anders Skaarup Johansen; Kamal Nasrollahi; Sergio Escalera; Thomas B. Moeslund |
|
| |
Title |
Who Cares about the Weather? Inferring Weather Conditions for Weather-Aware Object Detection in Thermal Images |
Type |
Journal Article |
| |
Year |
2023 |
Publication |
Applied Sciences |
Abbreviated Journal |
AS |
|
| |
Volume |
13 |
Issue |
18 |
Pages |
|
|
| |
Keywords |
thermal; object detection; concept drift; conditioning; weather recognition |
|
| |
Abstract |
Deployments of real-world object detection systems often experience a degradation in performance over time due to concept drift. Systems that leverage thermal cameras are especially susceptible because the respective thermal signatures of objects and their surroundings are highly sensitive to environmental changes. In this study, two types of weather-aware latent conditioning methods are investigated. The proposed method aims to guide two object detectors, (YOLOv5 and Deformable DETR) to become weather-aware. This is achieved by leveraging an auxiliary branch that predicts weather-related information while conditioning intermediate layers of the object detector. While the conditioning methods proposed do not directly improve the accuracy of baseline detectors, it can be observed that conditioned networks manage to extract a weather-related signal from the thermal images, thus resulting in a decreased miss rate at the cost of increased false positives. The extracted signal appears noisy and is thus challenging to regress accurately. This is most likely a result of the qualitative nature of the thermal sensor; thus, further work is needed to identify an ideal method for optimizing the conditioning branch, as well as to further improve the accuracy of the system. |
|
| |
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;MILAB |
Approved |
no |
|
| |
Call Number |
Admin @ si @ SNE2023 |
Serial |
3983 |
|
| Permanent link to this record |
