NextMotionQA benchmark reveals VLMs have critical gaps in fine-grained human motion understanding and align with experts on coarse judgment (κ=0.70) but not fine-grained (κ=0.10).
Motionllm: Understanding human behaviors from human motions and videos
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
WirelessSenseLLM bridges unsegmented Wi-Fi CSI signals to LLMs via a CSI-to-Language Adapter for zero-shot human activity understanding and reasoning.
MotionHiFlow generates text-aligned 3D human motions using hierarchical flow matching across temporal scales, cross-scale transitions, a Text-Motion Diffusion Transformer, and a topology-aware Motion VAE, achieving state-of-the-art results on HumanML3D and KIT-ML.
IMU-to-4D uses wearable IMU data and repurposed LLMs to predict coherent 4D human motion plus coarse scene structure, outperforming cascaded state-of-the-art pipelines in temporal stability.
MASS adds spatiotemporal motion signals and 3D grounding to VLMs and releases MASS-Bench, yielding physics-reasoning performance within 2% of Gemini-2.5-Flash after reinforcement fine-tuning.
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.
citing papers explorer
-
NextMotionQA: Benchmarking and Judging Human Motion Understanding with Vision-Language Models
NextMotionQA benchmark reveals VLMs have critical gaps in fine-grained human motion understanding and align with experts on coarse judgment (κ=0.70) but not fine-grained (κ=0.10).
-
WirelessSenseLLM: Zero-Shot Human Activity Understanding by Bridging Wireless Signals and Human Language
WirelessSenseLLM bridges unsegmented Wi-Fi CSI signals to LLMs via a CSI-to-Language Adapter for zero-shot human activity understanding and reasoning.
-
MotionHiFlow: Text-to-motion via hierarchical flow matching
MotionHiFlow generates text-aligned 3D human motions using hierarchical flow matching across temporal scales, cross-scale transitions, a Text-Motion Diffusion Transformer, and a topology-aware Motion VAE, achieving state-of-the-art results on HumanML3D and KIT-ML.
-
Seeing Without Eyes: 4D Human-Scene Understanding from Wearable IMUs
IMU-to-4D uses wearable IMU data and repurposed LLMs to predict coherent 4D human motion plus coarse scene structure, outperforming cascaded state-of-the-art pipelines in temporal stability.
-
MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models
MASS adds spatiotemporal motion signals and 3D grounding to VLMs and releases MASS-Bench, yielding physics-reasoning performance within 2% of Gemini-2.5-Flash after reinforcement fine-tuning.
-
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.