Pocket-STVG: lightweight architecture for Spatio-Temporal Video Grounding

arXiv:2609.31135 · cs.CV, cs.AI, cs.MM · Submitted 2026-09-25 · Read on arXiv

cs.CV, cs.AI, cs.MM

Submitted: 2026-09-25

Updated: 2026-09-25

Terminology

• Grounding — 70× in this paper · explained in 3 episodes
• Spatio-Temporal Video Grounding — 17× in this paper
• Embeddings — 14× in this paper · explained in 2 episodes
• Transformer — 14× in this paper · explained in 2 episodes
• Alignment — 13× in this paper · explained in 1 episode
• Accuracy — 6× in this paper · explained in 1 episode
• Distillation — 4× in this paper · explained in 2 episodes
• Spatio-temporal grounding — 4× in this paper · explained in 2 episodes
• Foundation Model — 3× in this paper · explained in 3 episodes
• Foundation Models — 3× in this paper · explained in 7 episodes
• Temporal Reasoning — 3× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Edge Devices — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Temporal Video Encoder — 2× in this paper
• Ablation — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Spatial Image Decoder — 1× in this paper
• Spatial Image Encoder — 1× in this paper
• Temporal consistency — 1× in this paper · explained in 2 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes

Sources

• SimBase: A Simple Baseline for Temporal Video Grounding
• Towards Long-Form Spatio-Temporal Video Grounding
• LLaVA-OneVision: Easy Visual Task Transfer
• RoBERTa: A Robustly Optimized BERT Pretraining Approach
• SAM 2: Segment Anything in Images and Videos
• Bridging Time and Space: Decoupled Spatio-Temporal Alignment for Video Grounding
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models