Showing 1–18 of 18 results
/ Date/ Name
Mar 7, 2024StableDrag: Stable Dragging for Point-based Image EditingMar 21, 2022MixFormer: End-to-End Tracking with Iterative Mixed AttentionApr 15, 2020Fully Convolutional Online TrackingMay 25, 2023MixFormerV2: Efficient Fully Transformer TrackingApr 1, 2021Target Transformed Regression for Accurate TrackingFeb 6, 2023MixFormer: End-to-End Tracking with Iterative Mixed AttentionApr 11, 2023SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports ScenesJul 2, 2024VFIMamba: Video Frame Interpolation with State Space ModelsJan 7, 2025Motion-Aware Generative Frame InterpolationOct 12, 2025LQRS: Learned Query Re-optimization Framework for Spark SQLAug 25, 2023Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object SegmentationSep 28, 2025HunyuanImage 3.0 Technical ReportJul 29, 2025MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDEOct 21, 2025SAM 2++: Tracking Anything at Any GranularityNov 24, 2025SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame PreservationAug 23, 2025HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio GenerationDec 3, 2024HunyuanVideo: A Systematic Framework For Large Video Generative ModelsMar 16, 2026HYDRA: Unifying Multi-modal Generation and Understanding via Representation-Harmonized Tokenization