RGB-Thermal (RGB-T) crowd counting leverages the complementary nature of visible light and thermal modalities for accurate counting. However, real-world scenarios often introduce challenges, such as misidentifying background elements like trees and lampposts as individuals, leading to inaccurate counts. Existing methods utilize segmentation as a preliminary procedure, which is constrained by segmentation accuracy. In this paper, we propose a novel method, utilizing the Segment Anything Model (SAM), to distinguish between the foreground and background of images. Specifically, we begin by utilizing SAM to obtain the semantic map of the original image. Subsequently, we extract the modality features and semantic features corresponding to the RGB and thermal modalities through multimodal feature extraction. These features are then fused using the Semantic-guide Feature Fusion module. Finally, the Multi-level Decoder is employed to generate the density map and the ultimate counting results. Our approach achieves state-of-the-art performance on the RGBT-CC dataset.

To support the replication of "MMSF: A Multimodal Sentiment-Fused Method to Recognize Video Speaking Style", which was presented at ICMR'23, this companion paper provides the details of the artifacts. Speaking style recognition is aimed at recognizing the styles of conversations, which provides a fine-grained description about talking. In the original paper, we proposed a novel multimodal sentiment-fused method, MMSF, which extracts and integrates visual, audio and textual features of videos and introduced sentiment in MMSF with cross-attention mechanism to enhance the video feature to recognize speaking styles. In this paper, we explain the details of the implement code and the dataset used for experiments.

As talking takes a large proportion of human lives, it is necessary to perform deeper understanding of human conversations. Speaking style recognition is aimed at recognizing the styles of conversations, which provides a fine-grained description about talking. Current works focus on adopting only visual clues to recognize speaking styles, which cannot accurately distinguish different speaking styles when they are visually similar. To recognize speaking styles more effectively, we propose a novel multimodal sentiment-fused method, MMSF, which extracts and integrates visual, audio and textual features of videos. In addition, as sentiment is one of the motivations of human behavior, we first introduce sentiment into our multimodal method with cross-attention mechanism, which enhance the video feature to recognize speaking styles. The proposed MMSF is evaluated on long-form video understanding benchmark, and the experiment results show that it is superior to the state-of-the-arts.

Pre-trained video-language models (VLMs) have shown superior performance in high-level video understanding tasks, analyzing multi-modal information, aligning with Deep Video Understanding Challenge (DVUC) requirements.In this paper, we explore pre-trained VLMs' potential in multimodal question answering for long-form videos. We propose a solution called Dual Branches Video Modeling (DBVM), which combines knowledge graph (KG) and VLMs, leveraging their strengths and addressing shortcomings.The KG branch recognizes and localizes entities, fuses multimodal features at different levels, and constructs KGs with entities as nodes and relationships as edges.The VLM branch applies a selection strategy to adapt input movies into acceptable length and a cross-matching strategy to post-process results providing accurate scene descriptions.Experiments conducted on the DVUC dataset validate the effectiveness of our DBVM.

RGB-Thermal salient object detection (RGB-T SOD) aims to locate salient objects in images that include both RGB and thermal information. Previous approaches often suggest designing a symmetric network structure to tackle the challenge of dealing with low-quality RGB or thermal images. However, we contend that RGB and thermal modalities possess different numbers of channels and disparities in information density. In this paper, we propose a novel asymmetric dual-stream network (ADNet). Specifically, we leverage an asymmetric backbone to extract four stages of RGB features and four stages of thermal features. To enable effective interaction among low-level features in the first two stages, we introduce the Channel-Spatial Interaction (CSI) module. In the last two stages, deep features are enhanced using the Self-Attention Enhancement (SAE) module. Experimental results on the VT5000, VT1000, and VT821 datasets attest to the superior performance of our proposed ADNet compared to state-of-the-art methods.

The Deep Video Understanding Challenge (DVUC) is aimed to use multiple modality information to build high-level understanding of video, involving tasks such as relationship recognition and interaction detection. In this paper, we use a joint learning framework to simultaneously predict multiple tasks with visual, text, audio and pose features. In addition, to answer the queries of DVUC, we design multiple answering strategies and use video language transformer which learns cross-modal information for matching videos with text choices. The final DVUC result shows that our method ranks first for group one of movie-level queries, and ranks third for both of group one and group two of scene-level queries.

The Deep Video Understanding Challenge (DVU) is a task that focuses on comprehending long duration videos which involve many entities. Its main goal is to build relationship and interaction knowledge graph between entities to answer relevant questions. In this paper, we improved the joint learning method which we previously proposed in many aspects, including few shot learning, optical flow feature, entity recognition, and video description matching. We verified the effectiveness of these measures through experiments.