Related papers: A Cross-Perspective Annotated Dataset for Dynamic …

Multi-Object Tracking (MOT) plays a critical role in analyzing player behavior from videos, enabling performance evaluation. Current MOT methods are often evaluated using publicly available datasets. However, most of these focus on everyday…

Transformer-based large language models (LLMs) excel in natural language processing tasks by capturing long-range dependencies through self-attention mechanisms. However, long-context modeling faces significant computational inefficiencies…

The development of autonomous vehicles provides an opportunity to have a complete set of camera sensors capturing the environment around the car. Thus, it is important for object detection and tracking to address new challenges, such as…

Event-based cameras are neuromorphic sensors capable of efficiently encoding visual information in the form of sparse sequences of events. Being biologically inspired, they are commonly used to exploit some of the computational and power…

Attention guidance is an approach to addressing dataset bias in deep learning, where the model relies on incorrect features to make decisions. Focusing on image classification tasks, we propose an efficient human-in-the-loop system to…

Interactive, real-time, and high-quality cloud video games pose a serious challenge to the Internet due to simultaneous high-throughput and low round trip delay requirements. In this paper, we investigate the traffic characteristics of…

While existing video benchmarks largely consider specialized downstream tasks like retrieval or question-answering (QA), contemporary multimodal AI systems must be capable of well-rounded common-sense reasoning akin to human visual…

In this work, we address the problem of 3D object detection from point cloud data in real time. For autonomous vehicles to work, it is very important for the perception component to detect the real world objects with both high accuracy and…

Advances in perception for self-driving cars have accelerated in recent years due to the availability of large-scale datasets, typically collected at specific locations and under nice weather conditions. Yet, to achieve the high safety…

One-shot transfer of dexterous grasps to novel scenes with object and context variations has been a challenging problem. While distilled feature fields from large vision models have enabled semantic correspondences across 3D scenes, their…

In the realm of object pose estimation, scenarios involving both dynamic objects and moving cameras are prevalent. However, the scarcity of corresponding real-world datasets significantly hinders the development and evaluation of robust…

Object recognition and object pose estimation in robotic grasping continue to be significant challenges, since building a labelled dataset can be time consuming and financially costly in terms of data collection and annotation. In this…

We then introduce a novel hierarchical knowledge distillation strategy that incorporates the similarity matrix, feature representation, and response map-based distillation to guide the learning of the student Transformer network. We also…

Multi-object tracking (MOT) is a critical and challenging task in computer vision, particularly in situations involving objects with similar appearances but diverse movements, as seen in team sports. Current methods, largely reliant on…

Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing methods reduce this cost along the sequence axis through local windows, kernel approximations, or token-level sparsity, but these…

The quadratic cost of attention limits the scalability of long-context LLMs, especially under limited hardware memory budgets. While attention is often sparse, existing static sparse methods cannot adapt to task- or input-dependent…

Accurately modelling human attention is essential for numerous computer vision applications, particularly in the domain of automotive safety. Existing methods typically collapse gaze into saliency maps or scanpaths, treating gaze dynamics…

Point cloud registration is a fundamental task in many applications such as localization, mapping, tracking, and reconstruction. Successful registration relies on extracting robust and discriminative geometric features. Though existing…

Transformers, renowned for their self-attention mechanism, have achieved state-of-the-art performance across various tasks in natural language processing, computer vision, time-series modeling, etc. However, one of the challenges with deep…

Point clouds are essential for object modeling and play a critical role in assisting driving tasks for autonomous vehicles (AVs). However, the significant volume of data generated by AVs creates challenges for storage, bandwidth, and…