Affect Expression Behaviour Analysis in the Wild using Spatio-Channel Attention and Complementary Context Information

• URL: http://arxiv.org/abs/2009.14440v2
• Date: Sat, 10 Oct 2020 06:24:19 GMT
• Title: Affect Expression Behaviour Analysis in the Wild using Spatio-Channel Attention and Complementary Context Information
• Authors: Darshan Gera and S Balasubramanian
• Abstract summary: Facial expression recognition in the wild is crucial for building reliable human-computer interactive systems. Current FER systems fail to perform well under various natural and un-controlled conditions. This report presents attention based framework used in our submission to expression recognition track of the Affective Behaviour Analysis in-the-wild (ABAW) 2020 competition.
• Score: 5.076419064097734
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Facial expression recognition(FER) in the wild is crucial for building reliable human-computer interactive systems. However, current FER systems fail to perform well under various natural and un-controlled conditions. This report presents attention based framework used in our submission to expression recognition track of the Affective Behaviour Analysis in-the-wild (ABAW) 2020 competition. Spatial-channel attention net(SCAN) is used to extract local and global attentive features without seeking any information from landmark detectors. SCAN is complemented by a complementary context information(CCI) branch which uses efficient channel attention(ECA) to enhance the relevance of features. The performance of the model is validated on challenging Aff-Wild2 dataset for categorical expression classification.

Related papers

• Open-Vocabulary Animal Keypoint Detection with Semantic-feature Matching [74.75284453828017]
  Open-Vocabulary Keypoint Detection (OVKD) task is innovatively designed to use text prompts for identifying arbitrary keypoints across any species. We have developed a novel framework named Open-Vocabulary Keypoint Detection with Semantic-feature Matching (KDSM) This framework combines vision and language models, creating an interplay between language features and local keypoint visual features.
  arXiv  Detail & Related papers  (2023-10-08T07:42:41Z)
• Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition [57.08108545219043]
  Recognizing novel sub-categories with scarce samples is an essential and challenging research topic in computer vision. Existing literature addresses this challenge by employing local-based representation approaches. This article proposes a novel model, Robust Saliency-aware Distillation (RSaD), for few-shot fine-grained visual recognition.
  arXiv  Detail & Related papers  (2023-05-12T00:13:17Z)
• GCA-Net : Utilizing Gated Context Attention for Improving Image Forgery Localization and Detection [0.9883261192383611]
  We propose a novel Gated Context Attention Network (GCA-Net) that utilizes the non-local attention block for global context learning. We show that our method outperforms state-of-the-art networks by an average of 4.2%-5.4% AUC on multiple benchmark datasets.
  arXiv  Detail & Related papers  (2021-12-08T14:13:14Z)
• Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation [76.2621758731288]
  We tackle the detection of out-of-distribution (OOD) objects in semantic segmentation. Our main contribution is a new OOD detection architecture called ObsNet associated with a dedicated training scheme based on Local Adversarial Attacks (LAA) We show it obtains top performances both in speed and accuracy when compared to ten recent methods of the literature on three different datasets.
  arXiv  Detail & Related papers  (2021-08-03T17:09:56Z)
• How Knowledge Graph and Attention Help? A Quantitative Analysis into Bag-level Relation Extraction [66.09605613944201]
  We quantitatively evaluate the effect of attention and Knowledge Graph on bag-level relation extraction (RE) We find that (1) higher attention accuracy may lead to worse performance as it may harm the model's ability to extract entity mention features; (2) the performance of attention is largely influenced by various noise distribution patterns; and (3) KG-enhanced attention indeed improves RE performance, while not through enhanced attention but by incorporating entity prior.
  arXiv  Detail & Related papers  (2021-07-26T09:38:28Z)
• Affect Expression Behaviour Analysis in the Wild using Consensual Collaborative Training [2.538209532048867]
  This report presents Consensual Collaborative Training (CCT) framework used in our submission to the Affective Behaviour Analysis in-the-wild (ABAW) 2021 competition. CCT co-trains three networks jointly using a convex combination of supervision loss and consistency loss. Co-training reduces overall error, and consistency loss prevents overfitting to noisy samples.
  arXiv  Detail & Related papers  (2021-07-08T04:28:21Z)
• SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption [72.35532598131176]
  We propose SCARF, a technique for contrastive learning, where views are formed by corrupting a random subset of features. We show that SCARF complements existing strategies and outperforms alternatives like autoencoders.
  arXiv  Detail & Related papers  (2021-06-29T08:08:33Z)
• Attention Transfer Network for Aspect-level Sentiment Classification [30.704053194980528]
  Aspect-level sentiment classification (ASC) aims to detect the sentiment polarity of a given opinion target in a sentence. Data scarcity causes the attention mechanism sometimes to fail to focus on the corresponding sentiment words of the target. We propose a novel Attention Transfer Network (ATN) in this paper, which can successfully exploit attention knowledge from document-level sentiment classification datasets.
  arXiv  Detail & Related papers  (2020-10-23T04:26:33Z)
• PIN: A Novel Parallel Interactive Network for Spoken Language Understanding [68.53121591998483]
  In the existing RNN-based approaches, ID and SF tasks are often jointly modeled to utilize the correlation information between them. The experiments on two benchmark datasets, i.e., SNIPS and ATIS, demonstrate the effectiveness of our approach. More encouragingly, by using the feature embedding of the utterance generated by the pre-trained language model BERT, our method achieves the state-of-the-art among all comparison approaches.
  arXiv  Detail & Related papers  (2020-09-28T15:59:31Z)
• Hierarchical Context Embedding for Region-based Object Detection [40.9463003508027]
  Hierarchical Context Embedding (HCE) framework can be applied as a plug-and-play component. To advance the recognition of context-dependent object categories, we propose an image-level categorical embedding module. Novel RoI features are generated by exploiting hierarchically embedded context information beneath both whole images and interested regions.
  arXiv  Detail & Related papers  (2020-08-04T05:33:22Z)
• Landmark Guidance Independent Spatio-channel Attention and Complementary Context Information based Facial Expression Recognition [5.076419064097734]
  Modern facial expression recognition (FER) architectures rely on external sources like landmark detectors for defining attention. In this work, an end-to-end architecture for FER is proposed that obtains both local and global attention per channel per spatial location. robustness and superior performance of the proposed model is demonstrated on both in-lab and in-the-wild datasets.
  arXiv  Detail & Related papers  (2020-07-20T17:33:32Z)

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.