PoseLLM: Enhancing Language-Guided Human Pose Estimation with MLP Alignment

• URL: http://arxiv.org/abs/2507.09139v1
• Date: Sat, 12 Jul 2025 04:53:39 GMT
• Title: PoseLLM: Enhancing Language-Guided Human Pose Estimation with MLP Alignment
• Abstract summary: We propose PoseLLM, the first Large Language Model (LLM)-based pose estimation framework that replaces the linear projector with a nonlinear vision-language connector.<n>Our work demonstrates that a simple yet powerful nonlinear connector significantly boosts localization accuracy without sacrificing generalization.
• Score: 1.820765907065129
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Human pose estimation traditionally relies on architectures that encode keypoint priors, limiting their generalization to novel poses or unseen keypoints. Recent language-guided approaches like LocLLM reformulate keypoint localization as a vision-language task, enabling zero-shot generalization through textual descriptions. However, LocLLM's linear projector fails to capture complex spatial-textual interactions critical for high-precision localization. To address this, we propose PoseLLM, the first Large Language Model (LLM)-based pose estimation framework that replaces the linear projector with a nonlinear MLP vision-language connector. This lightweight two-layer MLP with GELU activation enables hierarchical cross-modal feature transformation, enhancing the fusion of visual patches and textual keypoint descriptions. Trained exclusively on COCO data, PoseLLM achieves 77.8 AP on the COCO validation set, outperforming LocLLM by +0.4 AP, while maintaining strong zero-shot generalization on Human-Art and MPII. Our work demonstrates that a simple yet powerful nonlinear connector significantly boosts localization accuracy without sacrificing generalization, advancing the state-of-the-art in language-guided pose estimation. Code is available at https://github.com/Ody-trek/PoseLLM.

Related papers

• One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting [51.09550363815034]
  Scene text spotting requires high-precision alignment between textual recognition and spatial localization.<n>We propose Single-Patch Text Spotting (SPaTS), a vision-centric framework that routes each text instance through a single anchor visual token.<n>We show that SPaTS consistently and significantly outperforms both frontier closed-source MLLMs and OCR MLLMs.
  arXiv  Detail & Related papers  (2026-07-30T09:17:48Z)
• ExACT: Exemplar-Driven Calibrated Refinement for Training-Free Visual Grounding in Remote Sensing Images [51.53960096934913]
  Remote sensing visual grounding (RSVG) aims to locate specific objects in high-resolution RS imagery using free-form natural language descriptions.<n>Recent advances in multimodal large language models (MLLMs) show great potential for such open-vocabulary RSVG.<n>We propose Exemplar-driven Calibrated Refinement (ExACT), a training-free framework driven by a one-shot visual prompting mechanism.
  arXiv  Detail & Related papers  (2026-06-27T13:50:39Z)
• SignSparK: Efficient Multilingual Sign Language Production via Sparse Keyframe Learning [54.232148007248874]
  Current Sign Language Production (SLP) frameworks face a stark trade-off: direct text-to-pose models suffer from regression-to-the-mean effects.<n>We propose a novel training paradigm that leverages sparses to capture the true underlying distribution of human signing.<n>By predicting dense motion from these discrete anchors, our approach mitigates regression-to-the-mean while ensuring fluid articulation.
  arXiv  Detail & Related papers  (2026-03-11T06:02:36Z)
• Towards Pixel-Level VLM Perception via Simple Points Prediction [27.271487302305726]
  We present SimpleSeg, a strikingly simple yet highly effective approach to endow Multimodal Large Language Models (MLLMs) with native pixel-level perception.<n>Our method reframes segmentation as a simple sequence generation problem: the model directly predicts sequences of points.<n>We find that the standard MLLM architecture possesses a strong, inherent capacity for low-level perception that can be unlocked without any specialized architecture.
  arXiv  Detail & Related papers  (2026-01-27T05:50:40Z)
• Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning [63.109585527799005]
  GroundingAgent is a visual grounding framework that operates without task-specific fine-tuning.<n>It achieves an average zero-shot grounding accuracy of 65.1 % on widely-used benchmarks.<n>It also offers strong interpretability, transparently illustrating each reasoning step.
  arXiv  Detail & Related papers  (2025-11-24T03:11:08Z)
• CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues for Embodied Reference Understanding [55.33317649771575]
  Embodied Reference Understanding involves predicting the object that a person in the scene is referring to through both pointing gesture and language.<n>We propose a dual-model framework, where one model learns from the head-to-fingertip direction and the other from the wrist-to-fingertip direction.<n>We present the CLIP-Aware Pointing Ensemble module, which performs a hybrid ensemble based on CLIP features.
  arXiv  Detail & Related papers  (2025-07-29T15:00:21Z)
• Helping CLIP See Both the Forest and the Trees: A Decomposition and Description Approach [43.419607730361996]
  Vision-Language Models (VLMs) like CLIP achieve cross-modal alignment through contrastive learning.<n>Traditional prompt engineering relies on coarse-grained category labels, neglecting fine-grained local semantics.<n>We propose a plug-and-play solution that enables CLIP to process localized visual descriptors.
  arXiv  Detail & Related papers  (2025-07-04T10:24:26Z)
• TULIP: Towards Unified Language-Image Pretraining [60.99500935831526]
  We introduce T, an open-source, drop-in replacement for existing CLIP-like models.<n>Our method leverages generative data augmentation, enhanced image-image and text-text contrastive learning, and image/text reconstruction regularization to learn fine-grained visual features.<n>Our approach, scaling to over 1B parameters, outperforms existing state-of-the-art (SOTA) models across benchmarks.
  arXiv  Detail & Related papers  (2025-03-19T17:58:57Z)
• IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis [46.502962768034166]
  Zero-shot Referring Image identifies the instance mask that best aligns with a referring expression without training and fine-tuning.<n>Previous CLIP-based models exhibit a notable reduction in their capacity to discern relative spatial relationships of objects.<n>IteRPrimE outperforms previous state-of-the-art zero-shot methods, particularly excelling in out-of-domain scenarios.
  arXiv  Detail & Related papers  (2025-03-02T15:19:37Z)
• Low-Light Image Enhancement via Generative Perceptual Priors [75.01646333310073]
  We introduce a novel textbfLLIE framework with the guidance of vision-language models (VLMs)<n>We first propose a pipeline that guides VLMs to assess multiple visual attributes of the LL image and quantify the assessment to output the global and local perceptual priors.<n>To incorporate these generative perceptual priors to benefit LLIE, we introduce a transformer-based backbone in the diffusion process, and develop a new layer normalization (textittextbfLPP-Attn) guided by global and local perceptual priors.
  arXiv  Detail & Related papers  (2024-12-30T12:51:52Z)
• Locality Alignment Improves Vision-Language Models [55.275235524659905]
  Vision language models (VLMs) have seen growing adoption in recent years, but many still struggle with basic spatial reasoning errors.<n>Our goal is to resolve this with a vision backbone that effectively captures both local and global image semantics.<n>We propose a new efficient post-training stage for ViTs called locality alignment and a novel fine-tuning procedure called MaskEmbed.
  arXiv  Detail & Related papers  (2024-10-14T21:01:01Z)
• Language-Assisted Human Part Motion Learning for Skeleton-Based Temporal Action Segmentation [11.759374280422113]
  Skeleton-based Temporal Action involves the dense action classification of variable-length skeleton sequences. Current approaches apply graph-based networks to extract framewise, whole-body-level motion representations. We propose a novel method named Language-assisted Human Part Motion Representation (LPL) to extract fine-grained part-level motion representations.
  arXiv  Detail & Related papers  (2024-10-08T20:42:51Z)
• LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model [52.35027502274539]
  LocLLM is the first Large-Language Model based keypoint localization model. It takes images and text instructions as inputs and outputs the desired keypoint coordinates. It shows remarkable performance on standard 2D/3D keypoint localization benchmarks.
  arXiv  Detail & Related papers  (2024-06-07T05:58:35Z)
• Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition [77.93678598476149]
  We establish a novel Symmetrical Linguistic Feature Distillation framework (named CLIP-OCR) By cascading the CLIP image encoder with the reversed CLIP text encoder, a symmetrical structure is built with an image-to-text feature flow. Extensive experiments demonstrate the effectiveness of CLIP-OCR with 93.8% average accuracy on six popular STR benchmarks.
  arXiv  Detail & Related papers  (2023-10-08T04:00:20Z)
• Location-free Human Pose Estimation [29.327982113378408]
  Human pose estimation (HPE) usually requires large-scale training data to reach high performance. We propose a location-free framework without supervision of keypoint locations. Inspired by the CAM-based weakly-supervised object localization, we observe that the coarse keypoint locations can be acquired through the part-aware CAMs but unsatisfactory due to the gap between the fine-grained HPE and the object-level localization.
  arXiv  Detail & Related papers  (2022-05-25T09:56:37Z)
• Hire-MLP: Vision MLP via Hierarchical Rearrangement [58.33383667626998]
  Hire-MLP is a simple yet competitive vision architecture via rearrangement. The proposed Hire-MLP architecture is built with simple channel-mixing operations, thus enjoys high flexibility and inference speed. Experiments show that our Hire-MLP achieves state-of-the-art performance on the ImageNet-1K benchmark.
  arXiv  Detail & Related papers  (2021-08-30T16:11:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.