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

arXiv: https://arxiv.org/abs/2609.31135 · HTML: https://mlsanity.com/paper/2609.31135/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 43 of its 52 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 30 of 43)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [ShareGPT4Video: Improving Video Understanding and Generation with Better Captions](https://mlsanity.com/paper/2406.04325/) (2024)
- [What does CLIP know about a red circle? Visual prompt engineering for VLMs](https://mlsanity.com/paper/2304.06712/) (2023)
- [FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving](https://mlsanity.com/paper/2505.17685/) (2025)
- [FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization](https://mlsanity.com/paper/2303.14189/) (2023)
- [ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension](https://mlsanity.com/paper/2204.05991/) (2022)
- [Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences](https://mlsanity.com/paper/2001.06891/) (2020)
- [MobileOne: An Improved One millisecond Mobile Backbone](https://mlsanity.com/paper/2206.04040/) (2022)
- [Contrastive Learning for Weakly Supervised Phrase Grounding](https://mlsanity.com/paper/2006.09920/) (2020)
- [MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training](https://mlsanity.com/paper/2311.17049/) (2023)
- [CLIP-KD: An Empirical Study of CLIP Model Distillation](https://mlsanity.com/paper/2307.12732/) (2023)
- [Human-centric Spatio-Temporal Video Grounding With Visual Transformers](https://mlsanity.com/paper/2011.05049/) (2020)
- [Context-Guided Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2401.01578/) (2024)
- [Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2209.13306/) (2022)
- [Relation-aware Instance Refinement for Weakly Supervised Visual Grounding](https://mlsanity.com/paper/2103.12989/) (2021)
- [Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2401.00901/) (2023)
- [Spatio-temporal Person Retrieval via Natural Language Queries](https://mlsanity.com/paper/1704.07945/) (2017)

## Abstract (arXiv)

Spatio-Temporal Video Grounding (STVG) aims to localize the spatio-temporal tube in a video corresponding to a natural language query. While recent methods achieve strong performance in fully supervised, weakly supervised, and zero-shot settings, they typically rely on computationally expensive architectures, complex training pipelines, or multimodal large language models. We present Pocket-STVG (P-STVG), a lightweight cascade architecture that addresses STVG by combining efficient pre-trained components instead of large end-to-end models. P-STVG integrates a temporal-aware video encoder based on MobileViCLIP, a spatial encoder-decoder derived from MDETR, and a shared aligned text encoder. Temporal localization is performed through either a lightweight 1D U-Net or a simple thresholding strategy, enabling the same framework to operate in both weakly supervised and zero-shot settings. Furthermore, video representations are precomputed independently of the query, yielding an indexing-friendly pipeline for efficient inference and large-scale video collections. Despite requiring fewer than 90M parameters, P-STVG performs on par with weakly supervised methods and improves on earlier zero-shot approaches at a fraction of their memory and computational cost, establishing a favorable performance-efficiency trade-off for STVG.