AGCD-Net: Attention Guided Context Debiasing Network for Emotion Recognition

• URL: http://arxiv.org/abs/2507.09248v1
• Date: Sat, 12 Jul 2025 11:03:55 GMT
• Title: AGCD-Net: Attention Guided Context Debiasing Network for Emotion Recognition
• Authors: Varsha Devi, Amine Bohi, Pardeep Kumar,
• Abstract summary: We propose textbfAGCD-Net, an Attention Guided Context Debiasing model.<n>At the core of AGCD-Net is the Attention Guided - Causal Intervention Module (AG-CIM), which applies causal theory, perturbs context features, isolates spurious correlations, and performs an attention-driven correction guided by face features to context bias.<n> Experimental results on the CAER-S dataset demonstrate the effectiveness of AGCD-Net, achieving state-of-the-art performance and highlighting the importance of causal debiasing for robust emotion recognition in complex settings.
• Score: 0.7032245866317619
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Context-aware emotion recognition (CAER) enhances affective computing in real-world scenarios, but traditional methods often suffer from context bias-spurious correlation between background context and emotion labels (e.g. associating ``garden'' with ``happy''). In this paper, we propose \textbf{AGCD-Net}, an Attention Guided Context Debiasing model that introduces \textit{Hybrid ConvNeXt}, a novel convolutional encoder that extends the ConvNeXt backbone by integrating Spatial Transformer Network and Squeeze-and-Excitation layers for enhanced feature recalibration. At the core of AGCD-Net is the Attention Guided - Causal Intervention Module (AG-CIM), which applies causal theory, perturbs context features, isolates spurious correlations, and performs an attention-driven correction guided by face features to mitigate context bias. Experimental results on the CAER-S dataset demonstrate the effectiveness of AGCD-Net, achieving state-of-the-art performance and highlighting the importance of causal debiasing for robust emotion recognition in complex settings.

Related papers

• AlignRAG: Leveraging Critique Learning for Evidence-Sensitive Retrieval-Augmented Reasoning [61.28113271728859]
  RAG has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>Standard RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>In this work, we reinterpret RAG as Retrieval-Augmented Reasoning and identify a central but underexplored problem: textitReasoning Misalignment.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models [26.51079570548107]
  Large language models (LLMs) often exhibit Context Faithfulness Hallucinations.<n>We propose Dynamic Attention-Guided Context Decoding (DAGCD), a lightweight framework that leverages attention distributions and uncertainty signals in a single-pass decoding.
  arXiv  Detail & Related papers  (2025-01-02T05:07:06Z)
• Towards Context-Aware Emotion Recognition Debiasing from a Causal Demystification Perspective via De-confounded Training [14.450673163785094]
  Context-Aware Emotion Recognition (CAER) provides valuable semantic cues for recognizing the emotions of target persons. Current approaches invariably focus on designing sophisticated structures to extract perceptually critical representations from contexts. We present a Contextual Causal Intervention Module (CCIM) to de-confound the confounder.
  arXiv  Detail & Related papers  (2024-07-06T05:29:02Z)
• Two in One Go: Single-stage Emotion Recognition with Decoupled Subject-context Transformer [78.35816158511523]
  We present a single-stage emotion recognition approach, employing a Decoupled Subject-Context Transformer (DSCT) for simultaneous subject localization and emotion classification. We evaluate our single-stage framework on two widely used context-aware emotion recognition datasets, CAER-S and EMOTIC.
  arXiv  Detail & Related papers  (2024-04-26T07:30:32Z)
• Robust Emotion Recognition in Context Debiasing [12.487614699507793]
  Context-aware emotion recognition (CAER) has recently boosted the practical applications of affective computing techniques in unconstrained environments. Despite advancements, the biggest challenge remains due to context bias interference. We propose a counterfactual emotion inference (CLEF) framework to address the above issue.
  arXiv  Detail & Related papers  (2024-03-09T17:05:43Z)
• You Only Train Once: A Unified Framework for Both Full-Reference and No-Reference Image Quality Assessment [45.62136459502005]
  We propose a network to perform full reference (FR) and no reference (NR) IQA. We first employ an encoder to extract multi-level features from input images. A Hierarchical Attention (HA) module is proposed as a universal adapter for both FR and NR inputs. A Semantic Distortion Aware (SDA) module is proposed to examine feature correlations between shallow and deep layers of the encoder.
  arXiv  Detail & Related papers  (2023-10-14T11:03:04Z)
• Context De-confounded Emotion Recognition [12.037240778629346]
  Context-Aware Emotion Recognition (CAER) aims to perceive the emotional states of the target person with contextual information. A long-overlooked issue is that a context bias in existing datasets leads to a significantly unbalanced distribution of emotional states. This paper provides a causality-based perspective to disentangle the models from the impact of such bias, and formulate the causalities among variables in the CAER task.
  arXiv  Detail & Related papers  (2023-03-21T15:12:20Z)
• FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network [48.912196729711624]
  Few-shot semantic segmentation is the task of learning to locate each pixel of a novel class in a query image with only a few annotated support images. We propose a Feature-Enhanced Context-Aware Network (FECANet) to suppress the matching noise caused by inter-class local similarity. In addition, we propose a novel correlation reconstruction module that encodes extra correspondence relations between foreground and background and multi-scale context semantic features.
  arXiv  Detail & Related papers  (2023-01-19T16:31:13Z)
• Towards Unbiased Visual Emotion Recognition via Causal Intervention [63.74095927462]
  We propose a novel Emotion Recognition Network (IERN) to alleviate the negative effects brought by the dataset bias. A series of designed tests validate the effectiveness of IERN, and experiments on three emotion benchmarks demonstrate that IERN outperforms other state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-07-26T10:40:59Z)
• Out of Context: A New Clue for Context Modeling of Aspect-based Sentiment Analysis [54.735400754548635]
  ABSA aims to predict the sentiment expressed in a review with respect to a given aspect. The given aspect should be considered as a new clue out of context in the context modeling process. We design several aspect-aware context encoders based on different backbones.
  arXiv  Detail & Related papers  (2021-06-21T02:26:03Z)
• Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation [74.05906222376608]
  We propose adversarial self-supervision UDA (or ASSUDA) that maximizes the agreement between clean images and their adversarial examples by a contrastive loss in the output space. This paper is rooted in two observations: (i) the robustness of UDA methods in semantic segmentation remains unexplored, which pose a security concern in this field; and (ii) although commonly used self-supervision (e.g., rotation and jigsaw) benefits image tasks such as classification and recognition, they fail to provide the critical supervision signals that could learn discriminative representation for segmentation tasks.
  arXiv  Detail & Related papers  (2021-05-23T01:50:44Z)

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.