[ICLR 2024] SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction

[IJCV 2024] LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models

[ICCV 2023] Latent Action Composition for Skeleton-based Action Segmentation

[BMVC 2022] MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks

[ECCV2022] Latent Discriminant deterministic Uncertainty

[BMVC 2021 Oral] Official implementation of our paper "A Unified Framework for Real-world Skeleton-based Action Recognition" on Toyota Smarthome/Penn Action/NTU-RGB+D/Posetics datasets

[ICLR 22, TPAMI 24] LIA: Latent Image Animator

This repository contains a collection of surveys, datasets, papers, and codes, for predictive uncertainty estimation in deep learning models.

This is a repo of extension of VPN for Recognition of Activities of Daily Living

The implementations for SLURP: Side Learning Uncertainty for Regression Problems (BMVC 2021)

Walking on the Edge: Fast, Low-Distortion Adversarial Examples

Localize to Classify and Classify to Localize: Mutual Guidance in Object Detection

We propose UniPose, a unified framework for human pose estimation, based on our “Waterfall” Atrous Spatial Pooling architecture, that achieves state-of-art-results on several pose estimation metric…

PyTorch implementation for our paper Learning Character-Agnostic Motion for Motion Retargeting in 2D, SIGGRAPH 2019

This is the official PyTorch implementation of the CVPR 2020 paper "TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting".

Implementation for ICCV 2021 paper "ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification"

2018.02-03 internship in Hubert Curien Laboratory

[WACV 2021]"Guided Attentive Feature Fusion for Multispectral Pedestrian Detection"

Improved action recognition with Separable spatio-temporal attention using alternative Skeletal and Video pre-processing

Implementation for CVPR2021 paper "Joint Generative and Contrastive Learning for Unsupervised Person Re-identification"

Implementation for WACV2021 paper "Enhancing Diversity in Teacher-Student Networks via Asymmetric branches for Unsupervised Person Re-identification"

[WACV 2021] Selective Spatio-Temporal Aggregation based Pose Refinement System: Towards understanding human activities in real-world videos.

[CVPR 2020] G3AN: Disentangling Appearance and Motion for Video Generation

2s-AGCN on Smarthome (dataset for daily living)

3D pose estimation from video : LCRNet2D+VideoPose3D

Knee flexion/extension angles estimation for a person who walks towards an RGB-D camera