8 March 2024 in IEEE Transactions on Affective Computing
Most current methods for image emotion analysis suffer from the affective gap, in which features directly extracted from images are supervised by a single emotional label, which may not align with users' perceived emotions. To effectively address this limitation, this paper introduces a novel multi-stage perception approach inspired by the human staged emotion perception process. The proposed approach comprises three perception modules: entity perception, attribute perception, and emotion perception. The entity perception module identifies entities in images, while the attribute perception module captures the attribute content associated with each entity. Finally, the emotion perception module combines entity and attribute information to extract emotion features. Pseudo-labels of entities and attributes are generated through image segmentation and vision-language models to provide auxiliary guidance for network learning. A progressive understanding of entities and attributes allows the network to hierarchically extract semantic-level features for emotion analysis. Comprehensive experiments on image emotion classification, regression, and distribution learning demonstrate the superior performance of our multi-stage perception network.
1 July 1993 in Physical Review D
Soft production of hadrons in hadronic collisions is described in the geometrical branching model and implemented by the eikonal cascade code (ecco). It is shown that the major global features of multiparticle production can be reproduced by one essential characterization of the dynamics of branching, namely, a scaling law for the mass distribution of daughter clusters. Without further adjustment of any parameters, the event generator can produce local features of multiplicity fluctuations in agreement with the NA22 intermittency data. The scaling exponent is determined to be 1.522 at GeV, independent of the dimensionality of the intermittency analysis. It is shown that is approximately independent of the collision energy.
28 March 2024 in IEEE Transactions on Affective Computing
Although video affective content analysis has great potential in many applications, it has not been thoroughly studied due to limited datasets. In this paper, we construct a large-scale video affective dataset with danmu (VAD). It consists of 19,267 elaborately segmented video clips from user-generated videos. The VAD dataset is annotated by the crowdsourcing platform with discrete valence, arousal, and primary emotions, as well as the comparison of valence and arousal between two consecutive video clips. Unlike previous datasets, including only video clips, our proposed dataset also provides danmu, which is the real-time comment from users as they watch a video. Danmu provides extra information for video affective content analysis. As a preliminary assessment of the usability of our dataset, an analysis of inter-annotator consistency for each label is conducted using weighted Fleiss' Kappa, regular Fleiss' Kappa, intraclass correlation coefficient, and percent consensus. Besides, we also perform a statistical analysis of labels and danmu. Finally, video affective content analysis is conducted on our dataset and three typical methods (i.e., TFN, MulT, and MISA) are leveraged to provide benchmarks. We also demonstrate that danmu can significantly improve the performance of the video affective content analysis task on some labels. Our dataset is available for research purposes.