Image emotion classification (IEC) aims to extract the abstract emotions evoked in images. Recently, language-supervised methods such as contrastive language-image pretraining (CLIP) have demonstrated superior performance in image understanding. However, the underexplored task of IEC presents three major challenges: a tremendous training objective gap between pretraining and IEC, shared suboptimal prompts, and invariant prompts for all instances. In this study, we propose a general framework that effectively exploits the language-supervised CLIP method for the IEC task. First, a prompt-tuning method that mimics the pretraining objective of CLIP is introduced, to exploit the rich image and text semantics associated with CLIP. Subsequently, instance-specific prompts are automatically composed, conditioning them on the categories and image content of instances, diversifying the prompts, and thus avoiding suboptimal problems. Evaluations on six widely used affective datasets show that the proposed method significantly outperforms state-of-the-art methods (up to 9.29% accuracy gain on the EmotionROI dataset) on IEC tasks with only a few trained parameters. The code is publicly available at https://github.com/dsn0w/PT-DPC/for research purposes.
28 November 2022 in IEEE Transactions on Affective Computing
Image emotion classification is an important computer vision task to extract emotions from images. The methods for image emotion classification (IEC) are primarily based on label or distribution as a supervision signal, which neither has enough accessibility nor diversity, limiting the development of IEC research. Inspired by psychology research and the recent booming of large-scale pretrained language models. We figure out a language-supervised paradigm, which can cleverly combine the features of language and visual emotion to drive the visual model to gain stronger emotional discernment with language prompts. To practice the paradigm, we present a conceptually simple while empirically powerful framework for image emotion classification, SimEmotion. That we propose a prompt-based fine-tuning strategy to learn task-specific representations by composing a template with the emotion-level concept and entity-level information. Evaluations on four widely-used affective datasets, namely, Flickr and Instagram (FI), EmotionROI, Twitter I, and Twitter II, demonstrate that the proposed algorithm outperforms the state-of-the-art methods with a large margin ( i.e. , 8.42% absolute accuracy gain on EmotionROI) on image emotion classification tasks. Our codes will be publicly available for research purposes.
21 June 2019 in IEEE Transactions on Intelligent Transportation Systems
Fine-grained vehicle recognition is challenging due to the large intra-class variation in vehicle pose and viewpoint. Many existing methods, especially convolution neural network (CNN)-based methods, solve this problem via detecting and aligning parts individually, and do not consider the interaction between parts, which is very important for effective part detection and vehicle recognition. In this paper, we propose a global topology constraint network for fine-grained vehicle recognition, which adopts the constraint of global topology relationship to depict the interaction between parts and integrates it into CNN in an efficient way. Different CNNs for image classification truncated at intermediate layer can be used for part detection. The global topology relationship between parts is encoded into kernel of depthwise convolution layer, and can be learned from training images. The response under global topology constraint reflects the probability of topology relationship between parts existing in input image. All responses build the description for classification with translation invariance. Through training the whole network, the back-propagation of gradient information of kernel for global topology relationship will guide former layers to better detect useful parts, and thereby improve vehicle recognition. Our proposed method does not require additional annotation, such as bounding box or part annotation, and can be trained in an end-to-end way. We conduct comparison experiments on public Stanford Cars and CompCars datasets, which both show that our method achieves the state-of-the-art performance.
Weakly supervised group activity recognition deals with the dependence on individual-level annotations during understanding scenes involving multiple individuals, which is a challenging task. Existing methods either take the trained detectors to extract individual features or utilize the attention mechanisms for partial context encoding, followed by integration to form the final group-level representations. However, the detectors require individual-level annotations during the training phase and have a mis-detection issue, and the partial contexts extracted immediately from the whole complex scene are too ambiguous without the guidance of concrete semantics. In this paper, we investigate the hierarchical structure inherent in group-level labels to extract the fine-grained semantics without using detectors for weakly supervised group activity recognition. A multi-hot encoding strategy combined with a semantic encoder is first adopted to get the label semantics embeddings. The semantic and visual scene information are then fused through a semantic decoder to obtain activity-specific features. Lastly, we employ the multi-label classification and integrate the scores of hierarchical activity labels. Experimental results show that our proposed method achieves the state-of-the-art performance on three benchmarks, and the accuracy on the Volleyball dataset exceeds the second-best method by 2%.
12 December 2022 in IEEE Transactions on Circuits and Systems for Video Technology
Group activity recognition aims to recognize behaviors characterized by multiple individuals within a scene. Existing schemes rely on individual relation inference and usually take the individuals as tokens. Essentially they select the most relevant region of the group activity from the entire image while filtering out irrelevant background noises. However, these schemes require individual bounding box labeling in both training and testing stages. Since individuals have usually been presented at one scale, multi-scale individuals cannot be combined in an effective way. In this paper, we present a novel end-to-end hierarchical relation inference framework based on active spatial positions for group activity recognition. This framework is designed to locate active spatial positions and use them as visual tokens to infer the relations for token embeddings. It requires individual bounding box labeling only in the training stage while automatically eliminating the background after locating active spatial positions from the entire scene. The hierarchical relations can be naturally inferred based on the visual tokens at different scales, contributing to further performance improvement. Experimental results demonstrate that the proposed framework is competitive against existing schemes that require more laboring and computation to generate labels in both the training and testing stage.
Motion information has been widely exploited for group activity recognition in sports video. However, in order to model and extract the various motion information between the adjacent frames, existing algorithms only use the coarse video‐level labels as supervision cues. This may lead to the ambiguity of extracted features and the omission of changing rules of motion patterns that are also important sports video recognition. In this paper, a latent label mining strategy for group activity recognition in basketball videos is proposed. The authors' novel strategy allows them to obtain the latent labels set for marking different frames in an unsupervised way, and build the frame‐level and video‐level representations with two separate levels of supervision signal. Firstly, the latent labels of motion patterns are digged using the unsupervised hierarchical clustering technique. The generated latent labels are then taken as the frame‐level supervision signal to train a deep CNN for the frame‐level features extraction. Lastly, the frame‐level features are fed into an LSTM network to build the spatio‐temporal representation for group activity recognition. Experimental results on the public NCAA dataset demonstrate that the proposed algorithm achieves state‐of‐the‐art performance.