# Capturing Rich Behavior Representations: A Dynamic Action Semantic-Aware Graph Transformer for Video Captioning

arXiv: https://arxiv.org/abs/2502.13754 · HTML: https://mlsanity.com/paper/2502.13754/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 19 Feb 2025.

## Builds on (most cited first, 24 of 24)

- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [Graph Transformer Networks](https://mlsanity.com/paper/1911.06455/) (2019)
- [SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning](https://mlsanity.com/paper/2111.13196/) (2021)
- [IQA: Visual Question Answering in Interactive Environments](https://mlsanity.com/paper/1712.03316/) (2017)
- [Visual Question Answering: A Survey of Methods and Datasets](https://mlsanity.com/paper/1607.05910/) (2016)
- [Spatio-Temporal Graph for Video Captioning with Knowledge Distillation](https://mlsanity.com/paper/2003.13942/) (2020)
- [Object Relational Graph with Teacher-Recommended Learning for Video Captioning](https://mlsanity.com/paper/2002.11566/) (2020)
- [Translating Videos to Natural Language Using Deep Recurrent Neural Networks](https://mlsanity.com/paper/1412.4729/) (2014)
- [Describing Videos by Exploiting Temporal Structure](https://mlsanity.com/paper/1502.08029/) (2015)
- [CLIP4Caption: CLIP for Video Caption](https://mlsanity.com/paper/2110.06615/) (2021)
- [Memory-Attended Recurrent Network for Video Captioning](https://mlsanity.com/paper/1905.03966/) (2019)
- [End-to-end Concept Word Detection for Video Captioning, Retrieval, and Question Answering](https://mlsanity.com/paper/1610.02947/) (2016)
- [Controllable Video Captioning with POS Sequence Guidance Based on Gated Fusion Network](https://mlsanity.com/paper/1908.10072/) (2019)
- [Object-aware Aggregation with Bidirectional Temporal Graph for Video Captioning](https://mlsanity.com/paper/1906.04375/) (2019)
- [Hierarchical Modular Network for Video Captioning](https://mlsanity.com/paper/2111.12476/) (2021)
- [Translating Videos to Commands for Robotic Manipulation with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1710.00290/) (2017)
- [O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning](https://mlsanity.com/paper/2108.02359/) (2021)
- [SEM-POS: Grammatically and Semantically Correct Video Captioning](https://mlsanity.com/paper/2303.14829/) (2023)

## Abstract (arXiv)

Existing video captioning methods merely provide shallow or simplistic representations of object behaviors, resulting in superficial and ambiguous descriptions. However, object behavior is dynamic and complex. To comprehensively capture the essence of object behavior, we propose a dynamic action semantic-aware graph transformer. Firstly, a multi-scale temporal modeling module is designed to flexibly learn long and short-term latent action features. It not only acquires latent action features across time scales, but also considers local latent action details, enhancing the coherence and sensitiveness of latent action representations. Secondly, a visual-action semantic aware module is proposed to adaptively capture semantic representations related to object behavior, enhancing the richness and accurateness of action representations. By harnessing the collaborative efforts of these two modules,we can acquire rich behavior representations to generate human-like natural descriptions. Finally, this rich behavior representations and object representations are used to construct a temporal objects-action graph, which is fed into the graph transformer to model the complex temporal dependencies between objects and actions. To avoid adding complexity in the inference phase, the behavioral knowledge of the objects will be distilled into a simple network through knowledge distillation. The experimental results on MSVD and MSR-VTT datasets demonstrate that the proposed method achieves significant performance improvements across multiple metrics.