216 citations · 493 across the 31 of their papers we have counts for
36 papers
LAC: Latent Action Composition for Skeleton-based Action Segmentation
Di Yang, Yaohui Wang, Antitza Dantcheva +4
Skeleton-based action segmentation requires recognizing composable actions in untrimmed videos. Current approaches decouple this problem by first extracting local visual features f…
Self-Supervised Video Representation Learning via Latent Time Navigation
Di Yang, Yaohui Wang, Quan Kong +4
Self-supervised video representation learning aimed at maximizing similarity between different temporal segments of one video, in order to enforce feature persistence over time. Th…
Human-Scene Network: A Novel Baseline with Self-rectifying Loss for Weakly supervised Video Anomaly Detection
Snehashis Majhi, Rui Dai, Quan Kong +3
Video anomaly detection in surveillance systems with only video-level labels (i.e. weakly-supervised) is challenging. This is due to, (i) the complex integration of human and scene…
Learning Invariance from Generated Variance for Unsupervised Person Re-identification
Hao Chen, Yaohui Wang, Benoit Lagadec +2
This work focuses on unsupervised representation learning in person re-identification (ReID). Recent self-supervised contrastive learning methods learn invariance by maximizing the…
Synthetic Data in Human Analysis: A Survey
Indu Joshi, Marcel Grimmer, Christian Rathgeb +3
Deep neural networks have become prevalent in human analysis, boosting the performance of applications, such as biometric recognition, action recognition, as well as person re-iden…
THORN: Temporal Human-Object Relation Network for Action Recognition
Mohammed Guermal, Rui Dai, Francois Bremond
Most action recognition models treat human activities as unitary events. However, human activities often follow a certain hierarchy. In fact, many human activities are compositiona…
Latent Image Animator: Learning to Animate Images via Latent Space Navigation
Yaohui Wang, Di Yang, Francois Bremond +1
Due to the remarkable progress of deep generative models, animating images has become increasingly efficient, whereas associated results have become increasingly realistic. Current…
Unsupervised Lifelong Person Re-identification via Contrastive Rehearsal
Hao Chen, Benoit Lagadec, Francois Bremond
Existing unsupervised person re-identification (ReID) methods focus on adapting a model trained on a source domain to a fixed target domain. However, an adapted ReID model usually…
Multimodal Personality Recognition using Cross-Attention Transformer and Behaviour Encoding
Tanay Agrawal, Dhruv Agarwal, Michal Balazia +2
Personality computing and affective computing have gained recent interest in many research areas. The datasets for the task generally have multiple modalities like video, audio, la…
MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection
Rui Dai, Srijan Das, Kumara Kahatapitiya +2
Action detection is an essential and challenging task, especially for densely labelled datasets of untrimmed videos. The temporal relation is complex in those datasets, including c…
CTRN: Class-Temporal Relational Network for Action Detection
Rui Dai, Srijan Das, Francois Bremond
Action detection is an essential and challenging task, especially for densely labelled datasets of untrimmed videos. There are many real-world challenges in those datasets, such as…
FLAME: Facial Landmark Heatmap Activated Multimodal Gaze Estimation
Neelabh Sinha, Michal Balazia, Francois Bremond
3D gaze estimation is about predicting the line of sight of a person in 3D space. Person-independent models for the same lack precision due to anatomical differences of subjects, w…
Weakly-supervised Joint Anomaly Detection and Classification
Snehashis Majhi, Srijan Das, Francois Bremond +2
Anomaly activities such as robbery, explosion, accidents, etc. need immediate actions for preventing loss of human life and property in real world surveillance systems. Although th…
Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection
Rui Dai, Srijan Das, Francois Bremond
In video understanding, most cross-modal knowledge distillation (KD) methods are tailored for classification tasks, focusing on the discriminative representation of the trimmed vid…
UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition
Di Yang, Yaohui Wang, Antitza Dantcheva +3
Action recognition based on skeleton data has recently witnessed increasing attention and progress. State-of-the-art approaches adopting Graph Convolutional networks (GCNs) can eff…
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living
Srijan Das, Rui Dai, Di Yang +1
Many attempts have been made towards combining RGB and 3D poses for the recognition of Activities of Daily Living (ADL). ADL may look very similar and often necessitate to model fi…
ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification
Hao Chen, Benoit Lagadec, Francois Bremond
Unsupervised person re-identification (ReID) aims at learning discriminative identity features without annotations. Recently, self-supervised contrastive learning has gained increa…
How Unique Is a Face: An Investigative Study
Michal Balazia, S L Happy, Francois Bremond +1
Face recognition has been widely accepted as a means of identification in applications ranging from border control to security in the banking sector. Surprisingly, while widely acc…
InMoDeGAN: Interpretable Motion Decomposition Generative Adversarial Network for Video Generation
Yaohui Wang, Francois Bremond, Antitza Dantcheva
In this work, we introduce an unconditional video generative model, InMoDeGAN, targeted to (a) generate high quality videos, as well as to (b) allow for interpretation of the laten…
Joint Generative and Contrastive Learning for Unsupervised Person Re-identification
Hao Chen, Yaohui Wang, Benoit Lagadec +2
Recent self-supervised contrastive learning provides an effective approach for unsupervised person re-identification (ReID) by learning invariance from different views (transformed…
Enhancing Diversity in Teacher-Student Networks via Asymmetric branches for Unsupervised Person Re-identification
Hao Chen, Benoit Lagadec, Francois Bremond
The objective of unsupervised person re-identification (Re-ID) is to learn discriminative features without labor-intensive identity annotations. State-of-the-art unsupervised Re-ID…
Selective Spatio-Temporal Aggregation Based Pose Refinement System: Towards Understanding Human Activities in Real-World Videos
Di Yang, Rui Dai, Yaohui Wang +4
Taking advantage of human pose data for understanding human activities has attracted much attention these days. However, state-of-the-art pose estimators struggle in obtaining high…
Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection
Rui Dai, Srijan Das, Saurav Sharma +4
Designing activity detection systems that can be successfully deployed in daily-living environments requires datasets that pose the challenges typical of real-world scenarios. In t…
VPN: Learning Video-Pose Embedding for Activities of Daily Living
Srijan Das, Saurav Sharma, Rui Dai +2
In this paper, we focus on the spatio-temporal aspect of recognizing Activities of Daily Living (ADL). ADL have two specific properties (i) subtle spatio-temporal patterns and (ii)…