Browse Proceedings

Open-vocabulary Multiple Object Tracking (MOT) aims to generalize trackers to novel categories not in the training set. Currently, the best-performing methods are mainly based on pure appearance matching. Due to the complexity of motion patterns ...

Object detection is a main task in computer vision. Template matching is the reference method for detecting objects with arbitrary templates. However, template matching computational complexity depends on the rotation accuracy, being a limiting ...

Data augmentation has become an integral part of deep learning, as it is known to improve the generalization capabilities of neural networks. Since the most effective set of image transformations differs between tasks and domains, automatic data ...

Self-supervised learning is increasingly applied to Earth observation problems that leverage satellite and other remotely sensed data. Within satellite imagery, metadata such as time and location often hold significant semantic information that ...

We present an inverse image-formation module that can enhance the robustness of existing visual SLAM pipelines for casually captured scenarios. Casual video captures often suffer from motion blur and varying appearances, which degrade the final ...

Manually creating textures for 3D meshes is time-consuming, even for expert visual content creators. We propose a fast approach for automatically texturing an input 3D mesh based on a user-provided text prompt. Importantly, our approach ...

Category-level pose estimation is a challenging task with many potential applications in computer vision and robotics. Recently, deep-learning-based approaches have made great progress, but are typically hindered by the need for large datasets of ...

Recognizing and disentangling visual attributes from objects is a foundation to many computer vision applications. While large vision-language representations like CLIP had largely resolved the task of zero-shot object recognition, zero-shot ...

Immersive scene generation, notably panorama creation, benefits significantly from the adaptation of large pre-trained text-to-image (T2I) models for multi-view image generation. Due to the high cost of acquiring multi-view images, tuning-free ...${\mathrm{}}^{}$

We propose an approach for Open-World Instance Segmentation (OWIS), a task that aims to segment arbitrary unknown objects in images by generalizing from a limited set of annotated object classes during training. Our Segment Object System (SOS) ...

We present Lagrangian Hashing, a representation for neural fields combining the characteristics of fast training NeRF methods that rely on Eulerian grids (i.e. InstantNGP), with those that employ points equipped with features as a way to ...

Currently, there is relatively limited research on the background activity noise of event cameras in different brightness conditions, and the relevant real-world datasets are extremely scarce. This limitation contributes to the lack of robustness ...

Label noise is ubiquitous in real-world scenarios, posing a practical challenge to supervised models due to its effect in hurting the generalization performance of deep neural networks. Existing methods primarily employ the sample selection ...

Post-Training Quantization (PTQ) has received significant attention because it requires only a small set of calibration data to quantize a full-precision model, which is more practical in real-world applications in which full access to a large ...

Novel-view synthesis based on visible light has been extensively studied. In comparison to visible light imaging, thermal infrared imaging offers the advantage of all-weather imaging and strong penetration, providing increased possibilities for ...

In this paper, we construct a large-scale benchmark dataset for Ground-to-Aerial Video-based person Re-Identification, named G2A-VReID, which comprises 185,907 images and 5,576 tracklets, featuring 2,788 distinct identities. To our knowledge, this ...

Nucleus instance segmentation in histology images is crucial for a broad spectrum of clinical applications. Current dominant algorithms rely on regression of nuclear proxy maps. Distinguishing nucleus instances from the estimated maps requires ...

This paper introduces a novel approach to gaze target detection leveraging a head-local-global coordination framework. Unlike traditional methods that rely heavily on estimating gaze direction and identifying salient objects in global view images, ...

In this study, we introduce the 3D space attention module (3DSA) as a novel approach to address the drawback of multi-view 3D human pose estimation methods, which fail to recognize the object’s significance from diverse viewpoints. Specifically, ...

Contemporary makeup approaches primarily hinge on unpaired learning paradigms, yet they grapple with the challenges of inaccurate supervision (e.g., face misalignment) and sophisticated facial prompts (including face parsing, and landmark ...$\mathbf{}\mathbf{}$

Robotic grasping in clutters is a fundamental task in robotic manipulation. In this work, we propose an economic framework for 6-DoF grasp detection, aiming to economize the resource cost in training and meanwhile maintain effective grasp ...

3D semantic occupancy prediction aims to obtain 3D fine-grained geometry and semantics of the surrounding scene and is an important task for the robustness of vision-centric autonomous driving. Most existing methods employ dense grids such as ...

Personalized text-to-image models allow users to generate varied styles of images (specified with a sentence) for an object (specified with a set of reference images). While remarkable results have been achieved using diffusion-based generation ...

Vision Transformer (ViT) has become one of the most prevailing fundamental backbone networks in the computer vision community. Despite the high accuracy, deploying it in real applications raises critical challenges including the high computational ...

Contrastive Language Image Pre-training (CLIP) has recently demonstrated success across various tasks due to superior feature representation empowered by image-text contrastive learning. However, the instance discrimination method used by CLIP can ...

Conventional text-to-motion generation methods are usually trained on limited text-motion pairs, making them hard to generalize to open-vocabulary scenarios. Some works use the CLIP model to align the motion space and the text space, aiming to ...${}^{\mathrm{}}$

Infrared-visible object detection aims to achieve robust even full-day object detection by fusing the complementary information of infrared and visible images. However, highly dynamically variable complementary characteristics and commonly ...