Emotion Recognition in Context

Kosti, Ronak; Álvarez, Jose M.; Recasens, Adrià; Lapedriza, Àgata

doi:10.1109/cvpr.2017.212

Cited by 144 publications

(97 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To solve these limitations, some approaches using other visual clues have been proposed [21,22,13,14]. Nicolaou et al [21] used the location of shoulders and Schindler et al [22] used the body pose to recognize six emotion categories under controlled conditions.…”

Section: Related Workmentioning

confidence: 99%

“…Chen et al [13] detected events, objects, and scenes using pre-learned CNNs and fused each score with context fusion. In [14], manually annotated body bounding boxes and holistic images were leveraged. However, [14] have a limited ability to encode dynamic signals (i.e., video) to estimate the emotion.…”

Section: Related Workmentioning

confidence: 99%

“…Nevertheless, such contexts have been rarely considered in most existing emotion recognition methods and benchmarks. Some methods [13,14] have shown that emotion recognition performance can be significantly boosted by considering context information such as gesture and place [13,14]. In addition, in visual sentimental analysis [15,16] that recognizes the sentiment of an image, similar to emotion recognition but not tailored to humans, the holistic visual appearance was used to encode such contexts.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Context-Aware Emotion Recognition Networks

Lee

Kim

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

170

131

View full text Add to dashboard Cite

Traditional techniques for emotion recognition have focused on the facial expression analysis only, thus providing limited ability to encode context that comprehensively represents the emotional responses. We present deep networks for context-aware emotion recognition, called CAER-Net, that exploit not only human facial expression but also context information in a joint and boosting manner. The key idea is to hide human faces in a visual scene and seek other contexts based on an attention mechanism. Our networks consist of two sub-networks, including two-stream encoding networks to separately extract the features of face and context regions, and adaptive fusion networks to fuse such features in an adaptive fashion. We also introduce a novel benchmark for context-aware emotion recognition, called CAER, that is more appropriate than existing benchmarks both qualitatively and quantitatively. On several benchmarks, CAER-Net proves the effect of context for emotion recognition. Our dataset is available at

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Context-Aware Emotion Recognition Networks

Lee

Kim

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

170

131

View full text Add to dashboard Cite

show abstract

“…DenseNets accomplish significant improvements over the state-of-the-art on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). Moreover, before extracting holistic features by using DenseNets, we fine-tune the Densenents network on Emotic Dataset [16]. Group cohesion level is relevant to the group-level emotion or valance degree.…”

Section: Scene Featuresmentioning

confidence: 99%

Automatic Group Cohesiveness Detection With Multi-modal Features

Zhu

Guo

Barner

et al. 2019

2019 International Conference on Multimodal Interaction

View full text Add to dashboard Cite

Group cohesiveness is a compelling and often studied composition in group dynamics and group performance. The enormous number of web images of groups of people can be used to develop an effective method to detect group cohesiveness. This paper introduces an automatic group cohesiveness prediction method for the 7th Emotion Recognition in the Wild (EmotiW 2019) Grand Challenge in the category of Group-based Cohesion Prediction. The task is to predict the cohesive level for a group of people in images. To tackle this problem, a hybrid network including regression models which are separately trained on face features, skeleton features, and scene features is proposed. Predicted regression values, corresponding to each feature, are fused for the final cohesive intensity. Experimental results demonstrate that the proposed hybrid network is effective and makes promising improvements. A mean squared error (MSE) of 0.444 is achieved on the testing sets which outperforms the baseline MSE of 0.5.

show abstract

“…TBIR-style tags inferred from query-and-click logs can be used to train a deep-learning network for more informative labels towards better CBIR. Also, crowdsourcing could be a way towards more semantic labels (e.g., [19]), for example, to capture human activities or emotions (e.g., [9,13,18,33]). Nevertheless, there are still major shortcomings in the state-of-the-art.…”

Section: Introductionmentioning

confidence: 99%

Visir

Chowdhury

Tandon

Ferhatosmanoğlu

et al. 2018

Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

The social media explosion has populated the Internet with a wealth of images. There are two existing paradigms for image retrieval: 1) content-based image retrieval (CBIR), which has traditionally used visual features for similarity search (e.g., SIFT features), and 2) tag-based image retrieval (TBIR), which has relied on user tagging (e.g., Flickr tags). CBIR now gains semantic expressiveness by advances in deep-learning-based detection of visual labels. TBIR benefits from query-and-click logs to automatically infer more informative labels. However, learning-based tagging still yields noisy labels and is restricted to concrete objects, missing out on generalizations and abstractions. Click-based tagging is limited to terms that appear in the textual context of an image or in queries that lead to a click. This paper addresses the above limitations by semantically refining and expanding the labels suggested by learning-based object detection. We consider the semantic coherence between the labels for different objects, leverage lexical and commonsense knowledge, and cast the label assignment into a constrained optimization problem solved by an integer linear program. Experiments show that our method, called VISIR, improves the quality of the state-of-the-art visual labeling tools like LSDA and YOLO.

show abstract

Emotion Recognition in Context

Cited by 144 publications

References 16 publications

Context-Aware Emotion Recognition Networks

Context-Aware Emotion Recognition Networks

Automatic Group Cohesiveness Detection With Multi-modal Features

Visir

Contact Info

Product

Resources

About