Spatio-Temporal Multi-Order Interaction for Video Recognition
cs.CV, cs.AI, cs.LG
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens
- Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding
- Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
- The Kinetics Human Action Video Dataset
- UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer
- UniFormer: Unifying Convolution and Self-attention for Visual Recognition
- Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning
- TEAM-Net: Multi-modal Learning for Video Action Recognition with Partial Decoding
- TFCNet: Temporal Fully Connected Networks for Static Unbiased Temporal Reasoning
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs