Showing 1–20 of 24 results
/ Date/ Name
Apr 1, 2024LLMs are Good Sign Language TranslatorsMar 6, 2026Physical Simulator In-the-Loop Video GenerationApr 9, 2023Token Boosting for Robust Self-Supervised Visual Transformer Pre-trainingAug 25, 2023Distribution-Aligned Diffusion for Human Mesh RecoveryAug 27, 2023AI-Generated Content (AIGC) for Various Data Modalities: A SurveyApr 1, 2024Action Detection via an Image Diffusion ProcessApr 1, 2023GradMDM: Adversarial Attack on Dynamic NetworksJul 20, 2022ERA: Expert Retrieval and Assembly for Early Action PredictionMar 28, 2023System-status-aware Adaptive Network for Online Streaming Video UnderstandingApr 1, 2023Progressive Channel-Shrinking NetworkSep 3, 2022Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action RecognitionNov 30, 2022DiffPose: Toward More Reliable 3D Pose EstimationJul 21, 2020Split and Expand: An inference-time improvement for Weakly Supervised Cell Instance SegmentationAug 26, 2024Avatar Concept Slider: Controllable Editing of Concepts in 3D Human AvatarsOct 13, 2022Improving the Reliability for Confidence EstimationDec 10, 2025VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion DensificationOct 3, 2022Heatmap Distribution Matching for Human Pose EstimationJul 15, 2024Learning to Unlearn for Robust Machine UnlearningMay 21, 2024LAGA: Layered 3D Avatar Generation and Customization via Gaussian SplattingApr 19, 2025Visual Prompting for One-shot Controllable Video Editing without Inversion