# Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding

arXiv: https://arxiv.org/abs/2501.17053 · HTML: https://mlsanity.com/paper/2501.17053/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 68 references that are in the map.
- First posted on arXiv 28 Jan 2025.

## Builds on (most cited first, 30 of 47)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [BoT-SORT: Robust Associations Multi-Pedestrian Tracking](https://mlsanity.com/paper/2206.14651/) (2022)
- [GLIPv2: Unifying Localization and Vision-Language Understanding](https://mlsanity.com/paper/2206.05836/) (2022)
- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [Universal Instance Perception as Object Discovery and Retrieval](https://mlsanity.com/paper/2303.06674/) (2023)
- [DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection](https://mlsanity.com/paper/2209.09407/) (2022)
- [PromptDet: Towards Open-vocabulary Detection using Uncurated Images](https://mlsanity.com/paper/2203.16513/) (2022)
- [Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences](https://mlsanity.com/paper/2001.06891/) (2020)
- [Grounding of Textual Phrases in Images by Reconstruction](https://mlsanity.com/paper/1511.03745/) (2015)
- [Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone](https://mlsanity.com/paper/2206.07643/) (2022)
- [Contrastive Learning for Weakly Supervised Phrase Grounding](https://mlsanity.com/paper/2006.09920/) (2020)
- [TubeDETR: Spatio-Temporal Video Grounding with Transformers](https://mlsanity.com/paper/2203.16434/) (2022)
- [Human-centric Spatio-Temporal Video Grounding With Visual Transformers](https://mlsanity.com/paper/2011.05049/) (2020)
- [Weakly-Supervised Video Moment Retrieval via Semantic Completion Network](https://mlsanity.com/paper/1911.08199/) (2019)
- [Detecting Everything in the Open World: Towards Universal Object Detection](https://mlsanity.com/paper/2303.11749/) (2023)
- [Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video](https://mlsanity.com/paper/1906.02549/) (2019)
- [Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment](https://mlsanity.com/paper/1903.11649/) (2019)

## Built on by (most cited first, 10 of 10)

- [STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding](https://mlsanity.com/paper/2502.20678/) (2025)
- [Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2509.15178/) (2025)
- [A Large-Scale Analysis on Contextual Self-Supervised Video Representation Learning](https://mlsanity.com/paper/2504.06153/) (2025)
- [OmViD: Omni-supervised active learning for video action detection](https://mlsanity.com/paper/2508.13983/) (2025)
- [Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey](https://mlsanity.com/paper/2510.10671/) (2025)
- [GaitCrafter: Diffusion Model for Biometric Preserving Gait Synthesis](https://mlsanity.com/paper/2508.13300/) (2025)
- [RobustGait: Robustness Analysis for Appearance Based Gait Recognition](https://mlsanity.com/paper/2511.13065/) (2025)
- [VISTA: Video Interaction Spatio-Temporal Analysis Benchmark](https://mlsanity.com/paper/2605.01391/) (2026)
- [Training-Free Open-Vocabulary Visual Grounding for Remote Sensing Images and Videos](https://mlsanity.com/paper/2606.16124/) (2026)
- [Pocket-STVG: lightweight architecture for Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2609.31135/) (2026)

## Abstract (arXiv)

In this work, we focus on Weakly Supervised Spatio-Temporal Video Grounding (WSTVG). It is a multimodal task aimed at localizing specific subjects spatio-temporally based on textual queries without bounding box supervision. Motivated by recent advancements in multi-modal foundation models for grounding tasks, we first explore the potential of state-of-the-art object detection models for WSTVG. Despite their robust zero-shot capabilities, our adaptation reveals significant limitations, including inconsistent temporal predictions, inadequate understanding of complex queries, and challenges in adapting to difficult scenarios. We propose CoSPaL (Contextual Self-Paced Learning), a novel approach which is designed to overcome these limitations. CoSPaL integrates three core components: (1) Tubelet Phrase Grounding (TPG), which introduces spatio-temporal prediction by linking textual queries to tubelets; (2) Contextual Referral Grounding (CRG), which improves comprehension of complex queries by extracting contextual information to refine object identification over time; and (3) Self-Paced Scene Understanding (SPS), a training paradigm that progressively increases task difficulty, enabling the model to adapt to complex scenarios by transitioning from coarse to fine-grained understanding.