Related papers: Context-aware Deep Feature Compression for High-sp…
Semantic segmentation, which refers to pixel-wise classification of an image, is a fundamental topic in computer vision owing to its growing importance in robot vision and autonomous driving industries. It provides rich information about…
This paper is dedicated to an efficient compression of weights and optimizer states (called checkpoints) obtained at different stages during a neural network training process. First, we propose a prediction-based compression approach, where…
Visual object tracking under challenging conditions of motion and light can be hindered by the capabilities of conventional cameras, prone to producing images with motion blur. Event cameras are novel sensors suited to robustly perform…
Conventional multi-object tracking (MOT) systems are predominantly designed for pedestrian tracking and often exhibit limited generalization to other object categories. This paper presents a generalized tracking framework capable of…
In real-world scenarios, different features have different acquisition costs at test-time which necessitates cost-aware methods to optimize the cost and performance trade-off. This paper introduces a novel and scalable approach for…
Automatic art analysis aims to classify and retrieve artistic representations from a collection of images by using computer vision and machine learning techniques. In this work, we propose to enhance visual representations from neural…
Existing Visual Object Tracking (VOT) only takes the target area in the first frame as a template. This causes tracking to inevitably fail in fast-changing and crowded scenes, as it cannot account for changes in object appearance between…
Despite significant progress, RGB-based trackers remain vulnerable to challenging imaging conditions, such as low illumination and fast motion. Event cameras offer a promising alternative by asynchronously capturing pixel-wise brightness…
A major goal of computer vision is to enable computers to interpret visual situations---abstract concepts (e.g., "a person walking a dog," "a crowd waiting for a bus," "a picnic") whose image instantiations are linked more by their common…
Real-time, accurate prediction of human steering behaviors has wide applications, from developing intelligent traffic systems to deploying autonomous driving systems in both real and simulated worlds. In this paper, we present ContextVAE, a…
Discriminative correlation filters (DCF) with deep convolutional features have achieved favorable performance in recent tracking benchmarks. However, most of existing DCF trackers only consider appearance features of current frame, and…
While deep neural networks have achieved remarkable performance, data augmentation has emerged as a crucial strategy to mitigate overfitting and enhance network performance. These techniques hold particular significance in industrial…
Contextual reasoning with constraints is crucial for enhancing temporal consistency in cross-frame modeling for visual tracking. However, mainstream tracking algorithms typically associate context by merely stacking historical information…
Current Deep Learning methods for environment segmentation and velocity estimation rely on Convolutional Recurrent Neural Networks to exploit spatio-temporal relationships within obtained sensor data. These approaches derive scene dynamics…
We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning. Given an object tracker, our framework learns to fine-tune its model parameters in only a few iterations of…
Context awareness is an essential part of mobile and ubiquitous computing. Its goal is to unveil situational information about mobile users like locations and activities. The sensed context can enable many services like navigation, AR, and…
We propose in this paper a tracking algorithm which is able to adapt itself to different scene contexts. A feature pool is used to compute the matching score between two detected objects. This feature pool includes 2D, 3D displacement…
Self-supervised pre-trained transformers have improved the state of the art on a variety of speech tasks. Due to the quadratic time and space complexity of self-attention, they usually operate at the level of relatively short (e.g.,…
Object tracking has been broadly applied in unmanned aerial vehicle (UAV) tasks in recent years. However, existing algorithms still face difficulties such as partial occlusion, clutter background, and other challenging visual factors.…
Recently, deep learning methods have shown promising results in point cloud compression. For octree-based point cloud compression, previous works show that the information of ancestor nodes and sibling nodes are equally important for…