conftrace_

spatio-temporal token

7 papers

Explore in graph

Co-occurring keywords · papers mentioning both

channel-wise self-attention (1) template update (1) explicit visual prompt (1) masked video autoencoder (1) pre-trained image model (1) temporal redundancy (1) motion feature (1) multi-scale information (1) video large language model (1) surrogate modeling (1)

Papers

Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs ICCV 2025 PDE-Transformer: Efficient and Versatile Transformers for Physics Simulations ICML 2025 EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens ICML 2024 Explicit Visual Prompts for Visual Object Tracking AAAI 2024 HENASY: Learning to Assemble Scene-Entities for Interpretable Egocentric Video-Language Model NeurIPS 2024 Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation ICCV 2023 ViViT: A Video Vision Transformer ICCV 2021