Related papers: Symbolic-Vector Attention Fusion for Collective In…
Fusing LiDAR and image features in a homogeneous BEV domain has become popular for 3D object detection in autonomous driving. However, this paradigm is constrained by the excessive feature compression. While some works explore dense voxel…
In robotics, Vision-Language-Action (VLA) models that integrate diverse multimodal signals from multi-view inputs have emerged as an effective approach. However, most prior work adopts static fusion that processes all visual inputs…
In this paper, we present our submission to 3rd Affective Behavior Analysis in-the-wild (ABAW) challenge. Learningcomplex interactions among multimodal sequences is critical to recognise dimensional affect from in-the-wild audiovisual data.…
Concept Activation Vectors (CAVs) provide a powerful approach for interpreting deep neural networks by quantifying their sensitivity to human-defined concepts. However, when computed independently at different layers, CAVs often exhibit…
Large Vision-Language Models (LVLMs) represent a significant leap towards empathetic agents, demonstrating remarkable capabilities in emotion understanding. However, the internal mechanisms governing how LVLMs translate abstract visual…
Accurate classification of autonomous vehicle (AV) driving behaviors is critical for safety validation, performance diagnosis, and traffic integration analysis. However, existing approaches primarily rely on numerical time-series modeling…
We present a general framework for compositional action recognition -- i.e. action recognition where the labels are composed out of simpler components such as subjects, atomic-actions and objects. The main challenge in compositional action…
The ambiguity at the boundaries of different semantic classes in point cloud semantic segmentation often leads to incorrect decisions in intelligent perception systems, such as autonomous driving. Hence, accurate delineation of the…
Multi-modal large language models (MLLMs) advance vision language understanding but face inherent limitations in long-video tasks due to bounded perception context budgets. Existing agentic methods mitigate this via rule-based…
Managing connectivity in integrated satellite-terrestrial vehicular networks is critical for 6G, yet is challenged by dynamic conditions and partial observability. This letter introduces the Multi-Agent Actor-Critic with Satellite-Aided…
Marking anatomical landmarks in cephalometric radiography is a critical operation in cephalometric analysis. Automatically and accurately locating these landmarks is a challenging issue because different landmarks require different levels…
Value function factorization via centralized training and decentralized execution is promising for solving cooperative multi-agent reinforcement tasks. One of the approaches in this area, QMIX, has become state-of-the-art and achieved the…
News text classification is a crucial task in natural language processing, essential for organizing and filtering the massive volume of digital content. Traditional methods typically rely on statistical features like term frequencies or…
Agentic AI represents a transformative shift in artificial intelligence, but its rapid advancement has led to a fragmented understanding, often conflating modern neural systems with outdated symbolic models -- a practice known as conceptual…
Semantic change detection is an important task in geoscience and earth observation. By producing a semantic change map for each temporal phase, both the land use land cover categories and change information can be interpreted. Recently some…
Multi-agent LLM systems have demonstrated impressive capabilities in complex collaborative tasks, yet most frameworks treat communication as instantaneous and free, overlooking a fundamental constraint in real world teamwork, collaboration…
Recent advancements in semantic communication have primarily focused on image transmission, where neural network-based joint source-channel coding modules play a central role. However, such systems often experience semantic communication…
Vision-Language Models (VLMs) often yield inconsistent descriptions of the same object across viewpoints, hindering the ability of embodied agents to construct consistent semantic representations over time. Previous methods resolved…
To improve the prediction of cancer survival using whole-slide images and transcriptomics data, it is crucial to capture both modality-shared and modality-specific information. However, multimodal frameworks often entangle these…
We propose an audio-visual spatial-temporal deep neural network with: (1) a visual block containing a pretrained 2D-CNN followed by a temporal convolutional network (TCN); (2) an aural block containing several parallel TCNs; and (3) a…