ChatMotion: A Multimodal Multi-Agent for Human Motion Analysis
read the original abstract
Advancements in Multimodal Large Language Models (MLLMs) have improved human motion understanding. However, these models remain constrained by their "instruct-only" nature, lacking interactivity and adaptability for diverse analytical perspectives. To address these challenges, we introduce ChatMotion, a multimodal multi-agent framework for human motion analysis. ChatMotion dynamically interprets user intent, decomposes complex tasks into meta-tasks, and activates specialized function modules for motion comprehension. It integrates multiple specialized modules, such as the MotionCore, to analyze human motion from various perspectives. Extensive experiments demonstrate ChatMotion's precision, adaptability, and user engagement for human motion understanding.
This paper has not been read by Pith yet.
Forward citations
Cited by 7 Pith papers
-
URDF Synthesis from RGB-D Sequences via Differentiable Joint Inference and Energy-Consistent Verification
KinemaForge jointly infers part geometry, joint topology, and parameters from RGB-D sequences using a kinematic graph and differentiable dynamics, then verifies with an energy residual loss, reporting lower joint erro...
-
BCL: Bayesian In-Context Learning Framework for Information Extraction
BCL introduces a particle-filtering Bayesian update framework to systematically refine label representations in in-context learning for information extraction, claiming consistent gains over prior methods.
-
INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval
INTENT mitigates cross-modal correspondence noise and modality-inherent noise in composed image retrieval via FFT-based visual invariant composition and bi-objective discriminative learning.
-
HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval
HABIT improves robustness in composed image retrieval under noisy triplets by quantifying sample cleanliness via mutual information transition rates and applying dual-consistency progressive learning to retain good pa...
-
ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval
ReTrack calibrates directional bias in composed video features using semantic disentanglement and bidirectional evidence alignment to improve retrieval performance on CVR and CIR tasks.
-
Fine-grained Human Motion Understanding with Language Models
LLM model using explicit timestamped skeletal pose sequences and diverse pose/motion supervision achieves SOTA on multiple motion understanding benchmarks, including with 2D input surpassing prior 3D methods.
-
RAM: Recover Any 3D Human Motion in-the-Wild
RAM outperforms prior methods on PoseTrack and 3DPW for zero-shot multi-person 3D motion tracking and reconstruction by fusing semantic tracking, memory-augmented pose estimation, and predictive fusion.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.