Related papers: STAR-RT: Visual attention for real-time video game…
It remains challenging to automatically predict the multi-agent trajectory due to multiple interactions including agent to agent interaction and scene to agent interaction. Although recent methods have achieved promising performance, most…
The recurrent neural networks (RNN) can be used to solve the sequence to sequence problem, where both the input and the output have sequential structures. Usually there are some implicit relations between the structures. However, it is hard…
A commonly used technique for managing AI complexity in real-time strategy (RTS) games is to use action and/or state abstractions. High-level abstractions can often lead to good strategic decision making, but tactical decision quality may…
Modern robotic systems, deployed across domains from industrial automation to domestic assistance, face a critical challenge: executing tasks with precision and adaptability in dynamic, unpredictable environments. To address this, we…
Eye tracking (ET) can help to understand visual attention and cognitive processes in interactive environments. This study presents a comprehensive eye-tracking analysis framework of the Inhibitory Control Game, named the ReStroop game,…
Visual attention is a mechanism closely intertwined with vision and memory. Top-down information influences visual processing through attention. We designed a neural network model inspired by aspects of human visual attention. This model…
Understanding crowd motion dynamics is critical to real-world applications, e.g., surveillance systems and autonomous driving. This is challenging because it requires effectively modeling the socially aware crowd spatial interaction and…
First-person action recognition is a challenging task in video understanding. Because of strong ego-motion and a limited field of view, many backgrounds or noisy frames in a first-person video can distract an action recognition model during…
Table retrieval is the task of retrieving the most relevant tables from large-scale corpora given natural language queries. However, structural and semantic discrepancies between unstructured text and structured tables make embedding…
Attention is fundamental to both biological and artificial intelligence, yet research on animal attention and AI self attention remains largely disconnected. We propose a Recurrent Vision Transformer (Recurrent ViT) that integrates…
Channel and spatial attention mechanism has proven to provide an evident performance boost of deep convolution neural networks (CNNs). Most existing methods focus on one or run them parallel (series), neglecting the collaboration between…
Multimodal large language models excel across diverse domains but struggle with complex visual reasoning tasks. To enhance their reasoning capabilities, current approaches typically rely on explicit search or post-training techniques.…
We propose a video feature representation learning framework called STAR-GNN, which applies a pluggable graph neural network component on a multi-scale lattice feature graph. The essence of STAR-GNN is to exploit both the temporal dynamics…
Convolutional neural networks have enabled major progresses in addressing pixel-level prediction tasks such as semantic segmentation, depth estimation, surface normal prediction and so on, benefiting from their powerful capabilities in…
Thermal infrared (TIR) target tracking methods often adopt the correlation filter (CF) framework due to its computational efficiency. However, the low resolution of TIR images, along with tracking interference, significantly limits the…
Clinical 12-lead ECG classification remains difficult because of diverse recording conditions, overlapping pathologies, and pronounced label imbalance hinder generalization, while unconstrained augmentations risk distorting diagnostically…
In this paper, we propose Concentrate and Concentrate (CaC), a coarse-to-fine anomaly reward model based on Vision-Language Models. During inference, it first conducts a global temporal scan to anchor anomalous time windows, then performs…
Recently, tactile sensing has attracted great interest in robotics, especially for facilitating exploration of unstructured environments and effective manipulation. A detailed understanding of the surface textures via tactile sensing is…
Object-centric representation learning aims to decompose visual scenes into fixed-size vectors called "slots" or "object files", where each slot captures a distinct object. Current state-of-the-art object-centric models have shown…
Transforming complex actions into discrete skill abstractions has demonstrated strong potential for robotic manipulation. Existing approaches mainly leverage latent variable models, e.g., VQ-VAE, to learn skill abstractions through learned…