# Augmented 2D-TAN: A Two-stage Approach for Human-centric Spatio-Temporal Video Grounding

arXiv: https://arxiv.org/abs/2106.10634 · HTML: https://mlsanity.com/paper/2106.10634/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 7 references that are in the map.
- First posted on arXiv 20 Jun 2021.

## Builds on (most cited first, 7 of 7)

- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions](https://mlsanity.com/paper/1705.08421/) (2017)
- [A Short Note about Kinetics-600](https://mlsanity.com/paper/1808.01340/) (2018)
- [Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language](https://mlsanity.com/paper/1912.03590/) (2019)
- [Human-centric Spatio-Temporal Video Grounding With Visual Transformers](https://mlsanity.com/paper/2011.05049/) (2020)
- [Efficient Second-Order TreeCRF for Neural Dependency Parsing](https://mlsanity.com/paper/2005.00975/) (2020)

## Built on by (most cited first, 13 of 13)

- [Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding](https://mlsanity.com/paper/2109.04872/) (2021)
- [Context-Guided Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2401.01578/) (2024)
- [Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2401.00901/) (2023)
- [SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability](https://mlsanity.com/paper/2503.13983/) (2025)
- [Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2502.11168/) (2025)
- [SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses](https://mlsanity.com/paper/2408.01669/) (2024)
- [STVGFormer: Spatio-Temporal Video Grounding with Static-Dynamic Cross-Modal Understanding](https://mlsanity.com/paper/2207.02756/) (2022)
- [Towards Long-Form Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2602.23294/) (2026)
- [TubeRMC: Tube-conditioned Reconstruction with Mutual Constraints for Weakly-supervised Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2511.10241/) (2025)
- [Context Consistency Learning via Sentence Removal for Semi-Supervised Video Paragraph Grounding](https://mlsanity.com/paper/2506.18476/) (2025)
- [Unlocking the Potential of Grounding DINO in Videos: Parameter-Efficient Adaptation for Limited-Data Spatial-Temporal Localization](https://mlsanity.com/paper/2604.12346/) (2026)
- [Efficient Spatio-Temporal Grounding with Multimodal Large Models via Second-Level Tracking and RL Verification](https://mlsanity.com/paper/2606.29023/) (2026)
- [ScanFocus: A Coarse-to-Fine Framework for Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2607.13421/) (2026)

## Abstract (arXiv)

We propose an effective two-stage approach to tackle the problem of language-based Human-centric Spatio-Temporal Video Grounding (HC-STVG) task. In the first stage, we propose an Augmented 2D Temporal Adjacent Network (Augmented 2D-TAN) to temporally ground the target moment corresponding to the given description. Primarily, we improve the original 2D-TAN from two aspects: First, a temporal context-aware Bi-LSTM Aggregation Module is developed to aggregate clip-level representations, replacing the original max-pooling. Second, we propose to employ Random Concatenation Augmentation (RCA) mechanism during the training phase. In the second stage, we use pretrained MDETR model to generate per-frame bounding boxes via language query, and design a set of hand-crafted rules to select the best matching bounding box outputted by MDETR for each frame within the grounded moment.