A Paradigm Shift: Fully End-to-End Training for Temporal Sentence Grounding in Videos

Documenti analoghi

• ViSAudio: End-to-End Video-Driven Binaural Spatial Audio Generation
  di: Zhang, Mengchen, et al.
  Pubblicazione: (2025)
• SigFormer: Sparse Signal-Guided Transformer for Multi-Modal Human Action Segmentation
  di: Liu, Qi, et al.
  Pubblicazione: (2023)
• End-to-End Human Instance Matting
  di: Liu, Qinglin, et al.
  Pubblicazione: (2024)
• PropVG: End-to-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination
  di: Dai, Ming, et al.
  Pubblicazione: (2025)
• VLM-E2E: Enhancing End-to-End Autonomous Driving with Multimodal Driver Attention Fusion
  di: Liu, Pei, et al.
  Pubblicazione: (2025)