arXiv Computer Vision
HEIR: Learning Human-Entity Interactions with Functional Roles
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 10
IAE-VTG: Interaction-Aligned Action-Entity Video Temporal Grounding
arXiv:2609.09736v1 Announce Type: new Abstract: Video Temporal Grounding (VTG) localizes the video segment that matches a natural-language query. Many queries describe an action performed by a partic...
arXiv AI
Jun 30
Does Role Specialization Matter for Explanation Faithfulness in Mixture-of-Experts?
arXiv:2606. 29613v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have recently been extended with role-based mechanisms for interpretability.
arXiv Computer Vision
Sep 1
Hierarchical Relation-augmented Representation Generalization for Few-shot Action Recognition
arXiv:2504.10079v5 Announce Type: replace Abstract: Few-shot action recognition (FSAR) aims to recognize novel action categories with few exemplars. Existing methods typically learn frame-level repre...
arXiv AI
Aug 24
Identity-Aware Human-Object Interaction Motion Captioning
The paper introduces the Identity-Aware Human-Object Interaction Motion Captioning task, which requires captions to include both the subject’s identity and the interaction motion, e.g., "Sub_ID lifts the chair" instead of a generic description. It proposes ID‑HOINet, a model that learns from multi‑view videos using a Multi‑View Identity‑Motion Learning Module and a Two‑Stage Caption Rewriting Strategy to generate identity‑aware captions. Experiments show that ID‑HOINet achieves state‑of‑the‑art performance on the BEHAVE and InterCap datasets.
arXiv AI
Aug 12
Compositional Benchmark Synthesis for Hierarchical Human Action Recognition
arXiv:2608. 10765v1 Announce Type: new Abstract: Recognizing human behavior across levels of abstraction, from atomic actions to long-horizon intentions, requires data annotated along a semantic hierarchy.
arXiv Computer Vision
Aug 24
CogCanvas: A Benchmark for Evaluating Multi-Subject Reference-Based Image Generation
CogCanvas is a new benchmark for multi-subject reference-based image generation, featuring 1,952 curated reference images of 100 celebrities, 115 objects/fashion items, and 29 real-world backgrounds. It generates 1,361 compositional prompts with 2–5 people, using a pipeline that includes DINOv2 deduplication, aesthetic filtering, and automated graph derivation for interaction and positioning. The benchmark evaluates three tasks—reference-based multi-human-object generation, text-to-image compositional generation, and reference retrieval—under a six-axis protocol, and introduces BG‑Sim and Attr‑VQA metrics to assess background fidelity and attribute binding.