Search Results for author:
Found 33 papers, 16 papers with code
P-Age: Pexels Dataset for Robust Spatio-Temporal Apparent Age Classification
To address these challenges, we propose AgeFormer which utilizes spatio-temporal information on the dynamics of the entire body dominating face-based methods for age classification.
JOADAA: joint online action detection and action anticipation
By combining action anticipation and online action detection, our approach can cover the missing dependencies of future information in online action detection.
LAC: Latent Action Composition for Skeleton-based Action Segmentation
In this context, we propose Latent Action Composition (LAC), a novel self-supervised framework aiming at learning from synthesized composable motions for skeleton-based action segmentation.
Self-Supervised Video Representation Learning via Latent Time Navigation
Self-supervised video representation learning aimed at maximizing similarity between different temporal segments of one video, in order to enforce feature persistence over time.
Human-Scene Network: A Novel Baseline with Self-rectifying Loss for Weakly supervised Video Anomaly Detection
Video anomaly detection in surveillance systems with only video-level labels (i. e. weakly-supervised) is challenging.
Learning Invariance from Generated Variance for Unsupervised Person Re-identification
This work focuses on unsupervised representation learning in person re-identification (ReID).
LAC - Latent Action Composition for Skeleton-based Action Segmentation
In this context, we propose Latent Action Composition (LAC), a novel self-supervised framework aiming at learning from synthesized composable motions for skeleton-based action segmentation.
ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting
Current self-supervised approaches for skeleton action representation learning often focus on constrained scenarios, where videos and skeleton data are recorded in laboratory settings.
Synthetic Data in Human Analysis: A Survey
This survey is intended for researchers and practitioners in the field of human analysis.
THORN: Temporal Human-Object Relation Network for Action Recognition
In this work, we present an end-to-end network: THORN, that can leverage important human-object and object-object interactions to predict actions.
Latent Image Animator: Learning to Animate Images via Latent Space Navigation
Specifically, motion in generated video is constructed by linear displacement of codes in the latent space.
Unsupervised Lifelong Person Re-identification via Contrastive Rehearsal
Existing unsupervised person re-identification (ReID) methods focus on adapting a model trained on a source domain to a fixed target domain.
Unsupervised Domain Adaptation
Unsupervised Person Re-Identification
Multimodal Personality Recognition using Cross-Attention Transformer and Behaviour Encoding
Personality computing and affective computing have gained recent interest in many research areas.
MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection
Action detection is an essential and challenging task, especially for densely labelled datasets of untrimmed videos.
Ranked #2 on
Action Detection
on TSU
CTRN: Class-Temporal Relational Network for Action Detection
Action detection is an essential and challenging task, especially for densely labelled datasets of untrimmed videos.
Ranked #2 on
Action Detection
on Multi-THUMOS
FLAME: Facial Landmark Heatmap Activated Multimodal Gaze Estimation
3D gaze estimation is about predicting the line of sight of a person in 3D space.
Latent Image Animator: Learning to animate image via latent space navigation
Deviating from such models, we here introduce Latent Image Animator (LIA), a self-supervised auto-encoder that evades need for structure representation.
Weakly-supervised Joint Anomaly Detection and Classification
Thinking of a fully automatized surveillance system, which is capable of both detecting and classifying the anomalies that need immediate actions, a joint anomaly detection and classification method is a pressing need.
Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection
On the other hand, sequence-level distillation encourages the student to learn the temporal knowledge from the teacher, which consists of transferring the Global Contextual Relations and the Action Boundary Saliency.
UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition
This is achieved by learning an optimal dependency matrix from the uniform distribution based on a multi-head attention mechanism.
Ranked #1 on
Skeleton Based Action Recognition
on UPenn Action
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living
But the cost of computing 3D poses from RGB stream is high in the absence of appropriate sensors.
Ranked #9 on
Action Recognition
on NTU RGB+D 120
(using extra training data)
ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification
Then, we use similarity scores as soft pseudo labels to enhance the consistency between augmented and original views, which makes our model more robust to augmentation perturbations.
How Unique Is a Face: An Investigative Study
Face recognition has been widely accepted as a means of identification in applications ranging from border control to security in the banking sector.
InMoDeGAN: Interpretable Motion Decomposition Generative Adversarial Network for Video Generation
We design the architecture of InMoDeGAN-generator in accordance to proposed Linear Motion Decomposition, which carries the assumption that motion can be represented by a dictionary, with related vectors forming an orthogonal basis in the latent space.
PDAN: Pyramid Dilated Attention Network for Action Detection
Previous action detection methods fail in selecting the key temporal information in long videos.
Ranked #1 on
Action Detection
on TSU
Joint Generative and Contrastive Learning for Unsupervised Person Re-identification
In this context, we propose a mesh-based view generator.
Enhancing Diversity in Teacher-Student Networks via Asymmetric branches for Unsupervised Person Re-identification
The objective of unsupervised person re-identification (Re-ID) is to learn discriminative features without labor-intensive identity annotations.
Unsupervised Domain Adaptation
Unsupervised Person Re-Identification
Selective Spatio-Temporal Aggregation Based Pose Refinement System: Towards Understanding Human Activities in Real-World Videos
Taking advantage of human pose data for understanding human activities has attracted much attention these days.
Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection
Therefore, we propose a new baseline method for activity detection to tackle the novel challenges provided by our dataset.
VPN: Learning Video-Pose Embedding for Activities of Daily Living
The 2 key components of this VPN are a spatial embedding and an attention network.
Ranked #6 on
Action Classification
on Toyota Smarthome dataset
(using extra training data)
G3AN: Disentangling Appearance and Motion for Video Generation
Creating realistic human videos entails the challenge of being able to simultaneously generate both appearance, as well as motion.
Deep-Temporal LSTM for Daily Living Action Recognition
In this paper, we propose to improve the traditional use of RNNs by employing a many to many model for video classification.
Person Re-identification for Real-world Surveillance Systems
Current state-of-the-art methods often address the problem by relying on supervised learning of similarity metrics or ranking functions to implicitly model appearance transformation between cameras for each camera pair, or group, in the system.
