Related papers: Recursive Joint Attention for Audio-Visual Fusion …
Due to the severe lack of labeled data, existing methods of medical visual question answering usually rely on transfer learning to obtain effective image feature representation and use cross-modal fusion of visual and linguistic features to…
Intelligently reasoning about the world often requires integrating data from multiple modalities, as any individual modality may contain unreliable or incomplete information. Prior work in multimodal learning fuses input modalities only…
Music emotion recognition (MER), a sub-task of music information retrieval (MIR), has developed rapidly in recent years. However, the learning of affect-salient features remains a challenge. In this paper, we propose an end-to-end…
Empathetic and coherent responses are critical in auto-mated chatbot-facilitated psychotherapy. This study addresses the challenge of enhancing the emotional and contextual understanding of large language models (LLMs) in psychiatric…
We present Perceiver-VL, a vision-and-language framework that efficiently handles high-dimensional multimodal inputs such as long videos and text. Powered by the iterative latent cross-attention of Perceiver, our framework scales with…
Video caption refers to generating a descriptive sentence for a specific short video clip automatically, which has achieved remarkable success recently. However, most of the existing methods focus more on visual information while ignoring…
Emotion recognition plays a pivotal role in intelligent human-machine interaction systems. Multimodal approaches benefit from the fusion of diverse modalities, thereby improving the recognition accuracy. However, the lack of high-quality…
This paper introduces a new multi-modal model based on the Transformer architecture and tensor product fusion strategy, combining BERT's text vectors and ViT's image vectors to classify students' psychological conditions, with an accuracy…
Composed Video Retrieval (CoVR) facilitates video retrieval by combining visual and textual queries. However, existing CoVR frameworks typically fuse multimodal inputs in a single stage, achieving only marginal gains over initial baseline.…
The emotion detection technology to enhance human decision-making is an important research issue for real-world applications, but real-life emotion datasets are relatively rare and small. The experiments conducted in this paper use the…
Computer interfaces are advancing towards using multi-modalities to enable better human-computer interactions. The use of automatic emotion recognition (AER) can make the interactions natural and meaningful thereby enhancing the user…
Continuous emotion recognition in terms of valence and arousal under in-the-wild (ITW) conditions remains a challenging problem due to large variations in appearance, head pose, illumination, occlusions, and subject-specific patterns of…
We present a novel LSTM cell architecture capable of learning both intra- and inter-perspective relationships available in visual sequences captured from multiple perspectives. Our architecture adopts a novel recurrent joint learning…
Classifying group-level emotions is a challenging task due to complexity of video, in which not only visual, but also audio information should be taken into consideration. Existing works on multimodal emotion recognition are using bulky…
We present Attend-Fusion, a novel and efficient approach for audio-visual fusion in video classification tasks. Our method addresses the challenge of exploiting both audio and visual modalities while maintaining a compact model…
In this work, we explore the impact of visual modality in addition to speech and text for improving the accuracy of the emotion detection system. The traditional approaches tackle this task by fusing the knowledge from the various…
This paper presents our approach for the VA (Valence-Arousal) estimation task in the ABAW6 competition. We devised a comprehensive model by preprocessing video frames and audio segments to extract visual and audio features. Through the…
Multi-modal emotion recognition is challenging due to the difficulty of extracting features that capture subtle emotional differences. Understanding multi-modal interactions and connections is key to building effective bimodal speech…
In the latest social networks, more and more people prefer to express their emotions in videos through text, speech, and rich facial expressions. Multimodal video emotion analysis techniques can help understand users' inner world…
Spatial and temporal relationships, both short-range and long-range, between objects in videos, are key cues for recognizing actions. It is a challenging problem to model them jointly. In this paper, we first present a new variant of Long…