Pith. sign in

REVIEW 5 cited by

Joint Skeletal and Semantic Embedding Loss for Micro-gesture Classification

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2307.10624 v1 pith:SWYUKNNQ submitted 2023-07-20 cs.CV

Kun Li , Dan Guo , Guoliang Chen , Xinge Peng , Meng Wang This is my paper
classification cs.CV
keywords classificationmicro-gestureactionchallengeembeddinglosssemanticskeletal
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this paper, we briefly introduce the solution of our team HFUT-VUT for the Micros-gesture Classification in the MiGA challenge at IJCAI 2023. The micro-gesture classification task aims at recognizing the action category of a given video based on the skeleton data. For this task, we propose a 3D-CNNs-based micro-gesture recognition network, which incorporates a skeletal and semantic embedding loss to improve action classification performance. Finally, we rank 1st in the Micro-gesture Classification Challenge, surpassing the second-place team in terms of Top-1 accuracy by 1.10%.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. GMoT: Gated Motion-Aware Tokenization for Fine-Grained Micro-Gesture Video Reasoning with Multimodal LLMs

    cs.CV 2026-07 conditional novelty 5.0 of 10

    GMoT's gated motion tokens improve multimodal LLM micro-gesture recognition on iMiGUE and SMG, with limited support for reasoning-grounding claims.

  2. MM-Gesture: Towards Precise Micro-Gesture Recognition through Multimodal Fusion

    cs.CV 2025-07 conditional novelty 4.0 of 10

    Combining joint, limb, RGB, Taylor-video, optical-flow, and depth streams with two video backbones and a validation-tuned weighted ensemble reaches 73.213% top-1 accuracy on iMiGUE, the best MiGA challenge result to date.

  3. MAC 2026: Advancing Micro-Action Analysis Towards Fine-Grained Understanding

    cs.CV 2026-07 conditional novelty 3.0 of 10

    MAC 2026 reports a three-track micro-action challenge, adding a fine-grained MLLM-based understanding track evaluated on MA-Bench, with top-3 leaderboard results for each track.

  4. Online Micro-gesture Recognition Using Data Augmentation and Spatial-Temporal Attention

    cs.CV 2025-07 reject novelty 3.0 of 10

    The paper claims a first-place micro-gesture detection result from data augmentation and spatial-temporal attention, but its own table shows the winning F1 comes from the unmodified AdaTAD baseline, while the proposed...

  5. Towards Fine-Grained Emotion Understanding via Skeleton-Based Micro-Gesture Recognition

    cs.CV 2025-06 conditional novelty 3.0 of 10

    On the iMiGUE micro-gesture test set, a PoseC3D pipeline with a 41-joint skeleton, uniform-interval temporal sampling, and the MiGA 2023 semantic embedding loss reaches 67.01 percent Top-1 accuracy, ranking third in t...

Pith tools