SoftRerank: Hierarchical Soft Fusion with Candidate-Label Reranking for Long-Tailed Micro-Action Recognition

arXiv:2609.08221v1 Announce Type: new Abstract: Micro-actions are subtle, low-intensity non-verbal behaviors that provide cues to fine-grained human states, including emotions and intentions. Recognizing them remains difficult because they are brief, contain weak visual changes, and often exhibit similar motion patterns across categories. This paper addresses these challenges with a fine-grained micro-action recognition method that combines full fine-tuning of InternVideo2.5, hierarchical soft fusion, and a lightweight candidate-label reranker. For the long-tailed label distribution in MA-52, we use class-balanced sampling and inverse-frequency reweighting to reduce the effect of frequent classes during training. We fine-tune InternVideo2.5 end to end and attach coarse and group-conditional fine-grained classification heads to the shared video representation, improving the consistency between coarse and fine predictions. For ambiguous samples, the candidate-label reranker uses hard samples and video-label matching to focus on easily confused fine-grained actions. Experiments validate the proposed method, which achieves a 79.99% F1-mean on MA-52 and ranks first in the 3rd Micro-Action Analysis Grand Challenge at ACM Multimedia 2026.

Related

• Recognition-Conditioned Reasoning: A Training-Free Multimodal-LLM Pipeline for Fine-Grained Micro-Action Understanding
• MAC 2026: Advancing Micro-Action Analysis Towards Fine-Grained Understanding
• Micro-DualNet: Dual-Path Spatio-Temporal Network for Micro-Action Recognition
• B-MoE: A Body-Part-Aware Mixture-of-Experts 'All Parts Matter' Approach to Micro-Action Recognition
• HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning

Source: arXiv cs.CV | 2026-09-09