Related papers: Spatio-Temporal Attention for Consistent Video Sem…
Driver attention prediction is becoming an essential research problem in human-like driving systems. This work makes an attempt to predict the driver attention in driving accident scenarios (DADA). However, challenges tread on the heels of…
Bearing fault detection is a critical task in predictive maintenance, where accurate and timely fault identification can prevent costly downtime and equipment damage. Traditional attention mechanisms in Transformer neural networks often…
Deep learning models have enjoyed great success for image related computer vision tasks like image classification and object detection. For video related tasks like human action recognition, however, the advancements are not as significant…
Accurate and timely traffic flow forecasting is crucial for intelligent transportation systems. This paper presents a novel deep learning model, the Spatial-Temporal Unified Graph Attention Network (STGAtt). By leveraging a unified graph…
Spiking neural networks (SNNs) offer energy efficiency over artificial neural networks (ANNs) but suffer from high latency and computational overhead due to their multi-timestep operational nature. While various dynamic computation methods…
Dynamic scene graph generation aims at generating a scene graph of the given video. Compared to the task of scene graph generation from images, it is more challenging because of the dynamic relationships between objects and the temporal…
Semantic segmentation has achieved great accuracy in understanding spatial layout. For real-time tasks based on dynamic scenes, we extend semantic segmentation in temporal domain to enhance the spatial accuracy with motion. We utilize a…
Scene flow depicts the dynamics of a 3D scene, which is critical for various applications such as autonomous driving, robot navigation, AR/VR, etc. Conventionally, scene flow is estimated from dense/regular RGB video frames. With the…
The robustness of semantic segmentation on edge cases of traffic scene is a vital factor for the safety of intelligent transportation. However, most of the critical scenes of traffic accidents are extremely dynamic and previously unseen,…
Existing semi-supervised video object segmentation methods either focus on temporal feature matching or spatial-temporal feature modeling. However, they do not address the issues of sufficient target interaction and efficient parallel…
This paper proposes combining spatio-temporal appearance (STA) descriptors with optical flow for human action recognition. The STA descriptors are local histogram-based descriptors of space-time, suitable for building a partial…
Attention mechanisms have made significant strides in graph learning, yet they still exhibit notable limitations: local attention faces challenges in capturing long-range information due to the inherent problems of the message-passing…
This paper presents a new method for anomaly detection in automated systems with time and compute sensitive requirements, such as autonomous driving, with unparalleled efficiency. As systems like autonomous driving become increasingly…
The Detection Transformer (DETR) has revolutionized the design of CNN-based object detection systems, showcasing impressive performance. However, its potential in the domain of multi-frame 3D object detection remains largely unexplored. In…
Real-time video analysis remains a challenging problem in computer vision, requiring efficient processing of both spatial and temporal information while maintaining computational efficiency. Existing approaches often struggle to balance…
Textual cues are essential for everyday tasks like buying groceries and using public transport. To develop this assistive technology, we study the TextVQA task, i.e., reasoning about text in images to answer a question. Existing approaches…
Semantic segmentation in surgical videos has applications in intra-operative guidance, post-operative analytics and surgical education. Segmentation models need to provide accurate and consistent predictions since temporally inconsistent…
Video segmentation aims at partitioning video sequences into meaningful segments based on objects or regions of interest within frames. Current video segmentation models are often derived from image segmentation techniques, which struggle…
There is an increasing need of continual learning in dynamic systems, such as the self-driving vehicle, the surveillance drone, and the robotic system. Such a system requires learning from the data stream, training the model to preserve…
Dynamic representation learning plays a pivotal role in understanding the evolution of linguistic content over time. On this front both context and time dynamics as well as their interplay are of prime importance. Current approaches model…