SUTD Computer Vision & Learning Group (VLG)'s repositories
Animal-Kingdom
[CVPR2022] Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding
SUTD-TrafficQA
[CVPR2021] SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events
Chaotic-World
[ICCV2023] Chaotic World: A Large and Challenging Benchmark for Human Behavior Understanding in Chaotic Events
CLdetection2023
[MICCAI 2023 Challenge] Top solution of the MICCAI CLdetection2023 challenge
multi-modal-video-reasoning
[ICCV2021 Workshop] Multi-Modal Video Reasoning and Analyzing Competition
GradAuto
[ECCV2022] Gradauto: Energy-oriented attack on dynamic neural networks
GradMDM
[TPAMI2023] GradMDM: Adversarial Attack on Dynamic Networks
Progressive.Channel-Shrinking.Network
[TMM2023] Progressive Channel-Shrinking Network
VLMetaverse
[2024 ICME Workshop] Vision and Learning for an Enhanced Metaverse
LMC
[NeurIPS 2023] LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition
meta_confidence
[ECCV2022] Improving the Reliability for Confidence Estimation