Related papers: All-in-One Image Coding for Joint Human-Machine Vi…
Bundle adjustment (BA) is a fundamental optimization technique used in many crucial applications, including 3D scene reconstruction, robotic localization, camera calibration, autonomous driving, space exploration, street view map generation…
Joint compression of point cloud geometry and attributes is essential for efficient 3D data representation. Existing methods often rely on post-hoc recoloring procedures and manually tuned bitrate allocation between geometry and attribute…
Multi-accelerator servers are increasingly being deployed in shared multi-tenant environments (such as in cloud data centers) in order to meet the demands of large-scale compute-intensive workloads. In addition, these accelerators are…
Most existing methods for unsupervised domain adaptation (UDA) rely on a shared network to extract domain-invariant features. However, when facing multiple source domains, optimizing such a network involves updating the parameters of the…
State-of-the-art video object detection methods maintain a memory structure, either a sliding window or a memory queue, to enhance the current frame using attention mechanisms. However, we argue that these memory structures are not…
We present 3D-MPA, a method for instance segmentation on 3D point clouds. Given an input point cloud, we propose an object-centric approach where each point votes for its object center. We sample object proposals from the predicted object…
Model merging offers a scalable alternative to multi-task learning but often yields suboptimal performance on classification tasks. We attribute this degradation to a geometric misalignment between the merged encoder and static…
We consider multiple transmitters aiming to communicate their source signals (e.g., images) over a multiple access channel (MAC). Conventional communication systems minimize interference by orthogonally allocating resources (time and/or…
In recent years, the growing demand for medical imaging diagnosis has placed a significant burden on radiologists. As a solution, Medical Vision-Language Pre-training (Med-VLP) methods have been proposed to learn universal representations…
Video coding algorithms encode and decode an entire video frame while feature coding techniques only preserve and communicate the most critical information needed for a given application. This is because video coding targets human…
While recent image warping approaches achieved remarkable success on existing benchmarks, they still require training separate models for each specific task and cannot generalize well to different camera models or customized manipulations.…
The past decades have witnessed the rapid development of image and video coding techniques in the era of big data. However, the signal fidelity-driven coding pipeline design limits the capability of the existing image/video coding…
We propose a self-supervised shared encoder model that achieves strong results on several visual, language and multimodal benchmarks while being data, memory and run-time efficient. We make three key contributions. First, in contrast to…
Universal graph pre-training has emerged as a key paradigm in graph representation learning, offering a promising way to train encoders to learn transferable representations from unlabeled graphs and to effectively generalize across a wide…
Inter prediction is one of the key technologies enabling the high compression efficiency of modern video coding standards. 360-degree video needs to be mapped to the 2D image plane prior to coding in order to allow compression using…
Video coding, which targets to compress and reconstruct the whole frame, and feature compression, which only preserves and transmits the most critical information, stand at two ends of the scale. That is, one is with compactness and…
Ensemble methods combine the predictions of multiple models to improve performance, but they require significantly higher computation costs at inference time. To avoid these costs, multiple neural networks can be combined into one by…
Autonomous driving systems require a comprehensive understanding of the environment, achieved by extracting visual features essential for perception, planning, and control. However, models trained solely on single-task objectives or generic…
An increasing share of captured images and videos are transmitted for storage and remote analysis by computer vision algorithms, rather than to be viewed by humans. Contrary to traditional standard codecs with engineered tools, neural…
Multi-view image compression (MIC) aims to achieve high compression efficiency by exploiting inter-image correlations, playing a crucial role in 3D applications. As a subfield of MIC, distributed multi-view image compression (DMIC) offers…