KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension

• URL: http://arxiv.org/abs/2411.01846v1
• Date: Mon, 04 Nov 2024 06:42:24 GMT
• Title: KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension
• Authors: Jie Yang, Wang Zeng, Sheng Jin, Lumin Xu, Wentao Liu, Chen Qian, Ruimao Zhang,
• Abstract summary: We introduce Semantic Keypoint, which aims to comprehend keypoints across different task scenarios. We also introduce KptLLM, a unified multimodal model that utilizes an identify-then-detect strategy. KptLLM adeptly handles various modality inputs, facilitating the interpretation of both semantic contents and keypoint locations.
• Score: 31.283133365170052
• License:
• Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have greatly improved their abilities in image understanding. However, these models often struggle with grasping pixel-level semantic details, e.g., the keypoints of an object. To bridge this gap, we introduce the novel challenge of Semantic Keypoint Comprehension, which aims to comprehend keypoints across different task scenarios, including keypoint semantic understanding, visual prompt-based keypoint detection, and textual prompt-based keypoint detection. Moreover, we introduce KptLLM, a unified multimodal model that utilizes an identify-then-detect strategy to effectively address these challenges. KptLLM underscores the initial discernment of semantics in keypoints, followed by the precise determination of their positions through a chain-of-thought process. With several carefully designed modules, KptLLM adeptly handles various modality inputs, facilitating the interpretation of both semantic contents and keypoint locations. Our extensive experiments demonstrate KptLLM's superiority in various keypoint detection benchmarks and its unique semantic capabilities in interpreting keypoints.

Related papers

• CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models [18.121331575626023]
  Category-agnostic pose estimation (CAPE) has traditionally relied on support images with annotated keypoints. Recent efforts have begun exploring the use of text-based queries, where the need for support keypoints is eliminated. We introduce CapeLLM, a novel approach that leverages a text-based multimodal large language model (MLLM) for CAPE.
  arXiv  Detail & Related papers  (2024-11-11T11:08:26Z)
• KNN Transformer with Pyramid Prompts for Few-Shot Learning [52.735070934075736]
  Few-Shot Learning aims to recognize new classes with limited labeled data. Recent studies have attempted to address the challenge of rare samples with textual prompts to modulate visual features.
  arXiv  Detail & Related papers  (2024-10-14T07:39:30Z)
• Multi-Stream Keypoint Attention Network for Sign Language Recognition and Translation [3.976851945232775]
  Current approaches for sign language recognition rely on RGB video inputs, which are vulnerable to fluctuations in the background. We propose a multi-stream keypoint attention network to depict a sequence of keypoints produced by a readily available keypoint estimator. We carry out comprehensive experiments on well-known benchmarks like Phoenix-2014, Phoenix-2014T, and CSL-Daily to showcase the efficacy of our methodology.
  arXiv  Detail & Related papers  (2024-05-09T10:58:37Z)
• Meta-Point Learning and Refining for Category-Agnostic Pose Estimation [46.98479393474727]
  Category-agnostic pose estimation (CAPE) aims to predict keypoints for arbitrary classes given a few support images annotated with keypoints. We propose a novel framework for CAPE based on such potential keypoints (named as meta-points)
  arXiv  Detail & Related papers  (2024-03-20T14:54:33Z)
• Open-Vocabulary Animal Keypoint Detection with Semantic-feature Matching [74.75284453828017]
  Open-Vocabulary Keypoint Detection (OVKD) task is innovatively designed to use text prompts for identifying arbitrary keypoints across any species. We have developed a novel framework named Open-Vocabulary Keypoint Detection with Semantic-feature Matching (KDSM) This framework combines vision and language models, creating an interplay between language features and local keypoint visual features.
  arXiv  Detail & Related papers  (2023-10-08T07:42:41Z)
• Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding [54.49214267905562]
  We construct a transformer-based framework for multi-modal manipulation detection and grounding tasks. Our framework simultaneously explores modality-specific features while preserving the capability for multi-modal alignment. We propose an implicit manipulation query (IMQ) that adaptively aggregates global contextual cues within each modality.
  arXiv  Detail & Related papers  (2023-09-22T06:55:41Z)
• Keyphrase Extraction with Dynamic Graph Convolutional Networks and Diversified Inference [50.768682650658384]
  Keyphrase extraction (KE) aims to summarize a set of phrases that accurately express a concept or a topic covered in a given document. Recent Sequence-to-Sequence (Seq2Seq) based generative framework is widely used in KE task, and it has obtained competitive performance on various benchmarks. In this paper, we propose to adopt the Dynamic Graph Convolutional Networks (DGCN) to solve the above two problems simultaneously.
  arXiv  Detail & Related papers  (2020-10-24T08:11:23Z)
• MOPT: Multi-Object Panoptic Tracking [33.77171216778909]
  We introduce a novel perception task denoted as multi-object panoptic tracking (MOPT) MOPT allows for exploiting pixel-level semantic information of 'thing' and'stuff' classes, temporal coherence, and pixel-level associations over time. We present extensive quantitative and qualitative evaluations of both vision-based and LiDAR-based MOPT that demonstrate encouraging results.
  arXiv  Detail & Related papers  (2020-04-17T11:45:28Z)
• Towards High Performance Human Keypoint Detection [87.1034745775229]
  We find that context information plays an important role in reasoning human body configuration and invisible keypoints. Inspired by this, we propose a cascaded context mixer ( CCM) which efficiently integrates spatial and channel context information. To maximize CCM's representation capability, we develop a hard-negative person detection mining strategy and a joint-training strategy. We present several sub-pixel refinement techniques for postprocessing keypoint predictions to improve detection accuracy.
  arXiv  Detail & Related papers  (2020-02-03T02:24:51Z)

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.