Exploring Predicate Visual Context in Detecting Human-Object Interactions

• URL: http://arxiv.org/abs/2308.06202v2
• Date: Tue, 7 Nov 2023 23:05:26 GMT
• Title: Exploring Predicate Visual Context in Detecting Human-Object Interactions
• Authors: Frederic Z. Zhang, Yuhui Yuan, Dylan Campbell, Zhuoyao Zhong, Stephen Gould
• Abstract summary: We study how best to re-introduce image features via cross-attention. Our model with enhanced predicate visual context (PViC) outperforms state-of-the-art methods on the HICO-DET and V-COCO benchmarks.
• Score: 44.937383506126274
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recently, the DETR framework has emerged as the dominant approach for human--object interaction (HOI) research. In particular, two-stage transformer-based HOI detectors are amongst the most performant and training-efficient approaches. However, these often condition HOI classification on object features that lack fine-grained contextual information, eschewing pose and orientation information in favour of visual cues about object identity and box extremities. This naturally hinders the recognition of complex or ambiguous interactions. In this work, we study these issues through visualisations and carefully designed experiments. Accordingly, we investigate how best to re-introduce image features via cross-attention. With an improved query design, extensive exploration of keys and values, and box pair positional embeddings as spatial guidance, our model with enhanced predicate visual context (PViC) outperforms state-of-the-art methods on the HICO-DET and V-COCO benchmarks, while maintaining low training cost.

Related papers

• A Review of Human-Object Interaction Detection [6.1941885271010175]
  Human-object interaction (HOI) detection plays a key role in high-level visual understanding. This paper systematically summarizes and discusses the recent work in image-based HOI detection.
  arXiv  Detail & Related papers  (2024-08-20T08:32:39Z)
• Exploring Interactive Semantic Alignment for Efficient HOI Detection with Vision-language Model [3.3772986620114387]
  We introduce ISA-HOI, which extensively leverages knowledge from CLIP, aligning interactive semantics between visual and textual features. Our method achieves competitive results on the HICO-DET and V-COCO benchmarks with much fewer training epochs, and outperforms the state-of-the-art under zero-shot settings.
  arXiv  Detail & Related papers  (2024-04-19T07:24:32Z)
• Disentangled Interaction Representation for One-Stage Human-Object Interaction Detection [70.96299509159981]
  Human-Object Interaction (HOI) detection is a core task for human-centric image understanding. Recent one-stage methods adopt a transformer decoder to collect image-wide cues that are useful for interaction prediction. Traditional two-stage methods benefit significantly from their ability to compose interaction features in a disentangled and explainable manner.
  arXiv  Detail & Related papers  (2023-12-04T08:02:59Z)
• Enhancing HOI Detection with Contextual Cues from Large Vision-Language Models [56.257840490146]
  ConCue is a novel approach for improving visual feature extraction in HOI detection. We develop a transformer-based feature extraction module with a multi-tower architecture that integrates contextual cues into both instance and interaction detectors.
  arXiv  Detail & Related papers  (2023-11-26T09:11:32Z)
• Spatial Reasoning for Few-Shot Object Detection [21.3564383157159]
  We propose a spatial reasoning framework that detects novel objects with only a few training examples in a context. We employ a graph convolutional network as the RoIs and their relatedness are defined as nodes and edges, respectively. We demonstrate that the proposed method significantly outperforms the state-of-the-art methods and verify its efficacy through extensive ablation studies.
  arXiv  Detail & Related papers  (2022-11-02T12:38:08Z)
• Knowledge Guided Bidirectional Attention Network for Human-Object Interaction Detection [3.0915392100355192]
  We argue that the independent use of the bottom-up parsing strategy in HOI is counter-intuitive and could lead to the diffusion of attention. We introduce a novel knowledge-guided top-down attention into HOI, and propose to model the relation parsing as a "look and search" process. We implement the process via unifying the bottom-up and top-down attention in a single encoder-decoder based model.
  arXiv  Detail & Related papers  (2022-07-16T16:42:49Z)
• Exploiting Scene Graphs for Human-Object Interaction Detection [81.49184987430333]
  Human-Object Interaction (HOI) detection is a fundamental visual task aiming at localizing and recognizing interactions between humans and objects. We propose a novel method to exploit this information, through the scene graph, for the Human-Object Interaction (SG2HOI) detection task. Our method, SG2HOI, incorporates the SG information in two ways: (1) we embed a scene graph into a global context clue, serving as the scene-specific environmental context; and (2) we build a relation-aware message-passing module to gather relationships from objects' neighborhood and transfer them into interactions.
  arXiv  Detail & Related papers  (2021-08-19T09:40:50Z)
• ConsNet: Learning Consistency Graph for Zero-Shot Human-Object Interaction Detection [101.56529337489417]
  We consider the problem of Human-Object Interaction (HOI) Detection, which aims to locate and recognize HOI instances in the form of human, action, object> in images. We argue that multi-level consistencies among objects, actions and interactions are strong cues for generating semantic representations of rare or previously unseen HOIs. Our model takes visual features of candidate human-object pairs and word embeddings of HOI labels as inputs, maps them into visual-semantic joint embedding space and obtains detection results by measuring their similarities.
  arXiv  Detail & Related papers  (2020-08-14T09:11:18Z)
• Learning Human-Object Interaction Detection using Interaction Points [140.0200950601552]
  We propose a novel fully-convolutional approach that directly detects the interactions between human-object pairs. Our network predicts interaction points, which directly localize and classify the inter-action. Experiments are performed on two popular benchmarks: V-COCO and HICO-DET.
  arXiv  Detail & Related papers  (2020-03-31T08:42:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.