Related papers: SparseTT: Visual Tracking with Sparse Transformers

Achieving highly accurate and real-time 3D occupancy prediction from cameras is a critical requirement for the safe and practical deployment of autonomous vehicles. While this shift to sparse 3D representations solves the encoding…

Compressed Neural Networks have the potential to enable deep learning across new applications and smaller computational environments. However, understanding the range of learning tasks in which such models can succeed is not well studied.…

Vision Transformer (ViT) has emerged as a competitive alternative to convolutional neural networks for various computer vision applications. Specifically, ViT multi-head attention layers make it possible to embed information globally across…

3D Gaussian Splatting (3DGS) enables efficient training and fast novel view synthesis in static environments. To address challenges posed by transient objects, distractor-free 3DGS methods have emerged and shown promising results when dense…

In this paper, we present a new tracking architecture with an encoder-decoder transformer as the key component. The encoder models the global spatio-temporal feature dependencies between target objects and search regions, while the decoder…

In recent years, several progressive works promote the development of aerial tracking. One of the representative works is our previous work Fast-tracker which is applicable to various challenging tracking scenarios. However, it suffers from…

Visual object tracking is essential to intelligent robots. Most existing approaches have ignored the online latency that can cause severe performance degradation during real-world processing. Especially for unmanned aerial vehicles (UAVs),…

Existing visual change detectors usually adopt CNNs or Transformers for feature representation learning and focus on learning effective representation for the changed regions between images. Although good performance can be obtained by…

Siamese network based trackers formulate the visual tracking task as a similarity matching problem. Almost all popular Siamese trackers realize the similarity learning via convolutional feature cross-correlation between a target branch and…

We propose SFMNet, a novel 3D sparse detector that combines the efficiency of sparse convolutions with the ability to model long-range dependencies. While traditional sparse convolution techniques efficiently capture local structures, they…

Visual search is a ubiquitous challenge in natural vision, including daily tasks such as finding a friend in a crowd or searching for a car in a parking lot. Human rely heavily on relevant target features to perform goal-directed visual…

Region-based methods have become increasingly popular for model-based, monocular 3D tracking of texture-less objects in cluttered scenes. However, while they achieve state-of-the-art results, most methods are computationally expensive,…

Recently, Transformers have shown promising performance in various vision tasks. To reduce the quadratic computation complexity caused by the global self-attention, various methods constrain the range of attention within a local region to…

Self-attention in Transformers comes with a high computational cost because of their quadratic computational complexity, but their effectiveness in addressing problems in language and vision has sparked extensive research aimed at enhancing…

Monocular 3D object tracking aims to estimate temporally consistent 3D object poses across video frames, enabling autonomous agents to reason about scene dynamics. However, existing state-of-the-art approaches are fully supervised and rely…

Accurate and stable field-of-view (FoV) guidance is critical for safe and efficient minimally invasive surgery, yet existing approaches often conflate visual attention estimation with downstream camera control or rely on direct…

Modern vision transformers leverage visually inspired local interaction between pixels through attention computed within window or grid regions, in contrast to the global attention employed in the original ViT. Regional attention restricts…

Transformers are slow and memory-hungry on long sequences, since the time and memory complexity of self-attention are quadratic in sequence length. Approximate attention methods have attempted to address this problem by trading off model…

We propose an object tracking method, SFTrack++, that smoothly learns to preserve the tracked object consistency over space and time dimensions by taking a spectral clustering approach over the graph of pixels from the video, using a fast…

We propose a light-weight and highly efficient Joint Detection and Tracking pipeline for the task of Multi-Object Tracking using a fully-transformer architecture. It is a modified version of TransTrack, which overcomes the computational…