# TC-LLaVA: Rethinking the Transfer from Image to Video Understanding with Temporal Considerations

arXiv: https://arxiv.org/abs/2409.03206 · HTML: https://mlsanity.com/paper/2409.03206/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 22 of its 52 references that are in the map.
- First posted on arXiv 5 Sep 2024.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 22 of 22)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [CLEVRER: CoLlision Events for Video REpresentation and Reasoning](https://mlsanity.com/paper/1910.01442/) (2019)
- [PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning](https://mlsanity.com/paper/2404.16994/) (2024)
- [ST-LLM: Large Language Models Are Effective Temporal Learners](https://mlsanity.com/paper/2404.00308/) (2024)
- [An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM](https://mlsanity.com/paper/2403.18406/) (2024)
- [Vista-LLaMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens](https://mlsanity.com/paper/2312.08870/) (2023)
- [A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension](https://mlsanity.com/paper/2305.03347/) (2023)

## Built on by (most cited first, 6 of 6)

- [V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding](https://mlsanity.com/paper/2412.09616/) (2024)
- [Unleashing Hour-Scale Video Training for Long Video-Language Understanding](https://mlsanity.com/paper/2506.05332/) (2025)
- [Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspective](https://mlsanity.com/paper/2507.08801/) (2025)
- [Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuning](https://mlsanity.com/paper/2505.11945/) (2025)
- [C^2ROPE: Causal Continuous Rotary Positional Encoding for 3D Large Multimodal-Models Reasoning](https://mlsanity.com/paper/2602.10551/) (2026)
- [SigVLP: Sigmoid Volume-Language Pre-Training for Self-Supervised CT-Volume Adaptive Representation Learning](https://mlsanity.com/paper/2602.21735/) (2026)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) have significantly improved performance across various image-language applications. Recently, there has been a growing interest in adapting image pre-trained MLLMs for video-related tasks. However, most efforts concentrate on enhancing the vision encoder and projector components, while the core part, Large Language Models (LLMs), remains comparatively under-explored. In this paper, we propose two strategies to enhance the model's capability in video understanding tasks by improving inter-layer attention computation in LLMs. Specifically, the first approach focuses on the enhancement of Rotary Position Embedding (RoPE) with Temporal-Aware Dual RoPE, which introduces temporal position information to strengthen the MLLM's temporal modeling capabilities while preserving the relative position relationships of both visual and text tokens. The second approach involves enhancing the Attention Mask with the Frame-wise Block Causal Attention Mask, a simple yet effective method that broadens visual token interactions within and across video frames while maintaining the causal inference mechanism. Based on these proposed methods, we adapt LLaVA for video understanding tasks, naming it Temporal-Considered LLaVA (TC-LLaVA). Our TC-LLaVA achieves new state-of-the-art performance across various video understanding benchmarks with only supervised fine-tuning (SFT) on video-related datasets.