# HPE-CogVLM: Advancing Vision Language Models with a Head Pose Grounding Task

arXiv: https://arxiv.org/abs/2406.01914 · HTML: https://mlsanity.com/paper/2406.01914/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 53 of its 89 references that are in the map.
- First posted on arXiv 4 Jun 2024.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 30 of 53)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [Ferret: Refer and Ground Anything Anywhere at Any Granularity](https://mlsanity.com/paper/2310.07704/) (2023)
- [CrowdHuman: A Benchmark for Detecting Human in a Crowd](https://mlsanity.com/paper/1805.00123/) (2018)
- [3D Bounding Box Estimation Using Deep Learning and Geometry](https://mlsanity.com/paper/1612.00496/) (2016)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [Evolutionary Optimization of Model Merging Recipes](https://mlsanity.com/paper/2403.13187/) (2024)
- [AGORA: Avatars in Geography Optimized for Regression Analysis](https://mlsanity.com/paper/2104.14643/) (2021)
- [Reinforced Continual Learning](https://mlsanity.com/paper/1805.12369/) (2018)
- [Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation](https://mlsanity.com/paper/1804.06609/) (2018)
- [Gaze360: Physically Unconstrained Gaze Estimation in the Wild](https://mlsanity.com/paper/1910.10088/) (2019)
- [Panoptic Studio: A Massively Multiview System for Social Interaction Capture](https://mlsanity.com/paper/1612.03153/) (2016)
- [Fine-Grained Head Pose Estimation Without Keypoints](https://mlsanity.com/paper/1710.00925/) (2017)
- [Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild](https://mlsanity.com/paper/2207.10660/) (2022)

## Built on by (most cited first, 1 of 1)

- [EchoGen: Cycle-Consistent Learning for Unified Layout-Image Generation and Understanding](https://mlsanity.com/paper/2603.18001/) (2026)

## Abstract (arXiv)

Head pose estimation (HPE) requires a sophisticated understanding of 3D spatial relationships to generate precise yaw, pitch, and roll angles. Previous HPE models, primarily CNN-based, rely on cropped close-up human head images as inputs and often lack robustness in real-world scenario. Vision Language Models (VLMs) can analyze entire images while focusing on specific objects through their attention mechanisms. In this paper, we propose a novel framework to improve the HPE accuracy by leveraging the object detection grounding capability of a VLM, referred to as CogVLM. We empirically find that directly LoRA fine-tuning of this VLM for the HPE task fails to achieve desirable HPE accuracy, while some model merging methods can improve accuracy but frequently produce blended invalid response formats, struggling to handle both object detection and HPE tasks simultaneously. To integrate HPE capability into CogVLM effectively, we develop a novel LoRA layer-based model merging method. This merging approach applies a high cosine similarity threshold and a 'winner-takes-all' layer selection strategy, aligning attention to the HPE task while preserving original object detection knowledge. It successfully resolves issues with blended invalid response formats and improves accuracy. Results show that our HPE-CogVLM achieves a 31.5% reduction in Mean Absolute Error over the current state-of-the-art CNN model, 6DRepNet, in cross-dataset evaluation. Furthermore, HPE-CogVLM outperforms both directly LoRA fine-tuned and task arithmetic-based merged VLMs across all HPE metrics.