# Gaussian Kernel-based Cross Modal Network for Spatio-Temporal Video Grounding

arXiv: https://arxiv.org/abs/2207.00744 · HTML: https://mlsanity.com/paper/2207.00744/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 20 references that are in the map.
- First posted on arXiv 2 Jul 2022.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [MAttNet: Modular Attention Network for Referring Expression Comprehension](https://mlsanity.com/paper/1801.08186/) (2018)
- [Natural Language Object Retrieval](https://mlsanity.com/paper/1511.04164/) (2015)
- [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)
- [Dynamic Graph Attention for Referring Expression Comprehension](https://mlsanity.com/paper/1909.08164/) (2019)
- [Context-aware Biaffine Localizing Network for Temporal Sentence Grounding](https://mlsanity.com/paper/2103.11555/) (2021)
- [Jointly Cross- and Self-Modal Graph Attention Network for Query-Based Moment Localization](https://mlsanity.com/paper/2008.01403/) (2020)
- [Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video](https://mlsanity.com/paper/1906.02549/) (2019)
- [Object Referring in Videos with Language and Human Gaze](https://mlsanity.com/paper/1801.01582/) (2018)
- [Weakly-Supervised Video Object Grounding from Text by Loss Weighting and Object Interaction](https://mlsanity.com/paper/1805.02834/) (2018)
- [Spatio-temporal Person Retrieval via Natural Language Queries](https://mlsanity.com/paper/1704.07945/) (2017)

## Built on by (most cited first, 3 of 3)

- [Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective](https://mlsanity.com/paper/2605.26441/) (2026)
- [Transform-Equivariant Consistency Learning for Temporal Sentence Grounding](https://mlsanity.com/paper/2305.04123/) (2023)
- [Tracking Objects and Activities with Attention for Temporal Sentence Grounding](https://mlsanity.com/paper/2302.10813/) (2023)

## Abstract (arXiv)

Spatial-Temporal Video Grounding (STVG) is a challenging task which aims to localize the spatio-temporal tube of the interested object semantically according to a natural language query. Most previous works not only severely rely on the anchor boxes extracted by Faster R-CNN, but also simply regard the video as a series of individual frames, thus lacking their temporal modeling. Instead, in this paper, we are the first to propose an anchor-free framework for STVG, called Gaussian Kernel-based Cross Modal Network (GKCMN). Specifically, we utilize the learned Gaussian Kernel-based heatmaps of each video frame to locate the query-related object. A mixed serial and parallel connection network is further developed to leverage both spatial and temporal relations among frames for better grounding. Experimental results on VidSTG dataset demonstrate the effectiveness of our proposed GKCMN.