27 accepted papers
In the context of global population aging, the prevalence of neurodegenerative diseases is rapidly increasing. Vision-based impaired gait analysis emerges as a promising alternative for automatic and non-invasive diagnosis. While prior efforts have advanced either accuracy or interpretability of gai
Multiple kernel learning~(MKL), which borrows ideas from ensemble learning, aims to achieve improved generalization performance by treating individual kernels as base learners and combining them appropriately. However, existing MKL methods often lack comprehensive consideration of diversity among ba…
Multi-instance partial-label learning (MIPL) is a recently proposed learning paradigm to address tasks that multi-instance bags are associated with a candidate label set comprising one ground-truth label and several false positive labels. Existing MIPL methods rely on simple instance level informati…
The development of multimodal large language models (MLLMs) has advanced general video understanding. However, existing video evaluation benchmarks primarily focus on non-interactive videos, such as movies and recordings. To fill this gap, this paper proposes the first omnimodal benchmark for intera
Large language models (LLMs) can already draft plausible Triton kernels, yet most existing evaluations still focus on single-shot generation and underplay tool use and feedback. We introduce *TritonGym*, a benchmark and orchestration framework for evaluating agentic workflows in GPU code generation.…
In the rapidly evolving field of image generation, achieving precise control over generated content and maintaining semantic consistency remain significant limitations, particularly concerning grounding techniques and the necessity for model fine-tuning. To address these challenges, we propose Bayes…
Multimodal tracking has garnered widespread attention as a result of its ability to effectively address the inherent limitations of traditional RGB tracking. However, existing multimodal trackers mainly focus on the fusion and enhancement of spatial features or merely leverage the sparse temporal re…
Recently, several generalist models such as Contrastive Language Image Pre-training (CLIP) have demonstrated their capabilities of performing diverse downstream tasks through zero-shot or few-shot guidance. When these generalist models are used for the specific downstream task where only a fraction…
Consider a market with a seller and many buyers. The seller has a kind of item for sale to the buyers. The items have a quality and each buyer has a private type. The quality is only known to the seller, and the buyers only have a prior belief of the quality. A third party (e.g., intermediaries or p
This work presents a novel framework for Visual Localization (VL), that is, regressing camera rays from query images to derive camera poses. As an overparameterized representation of the camera pose, camera rays possess superior robustness in optimization.Of particular importance, Camera Ray Regress…
Outliers have been widely observed in Large Language Models (LLMs), significantly impacting model performance and posing challenges for model compression. Understanding the functionality and formation mechanisms of these outliers is critically important. Existing works, however, largely focus on red…
Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning tasks, yet their reliance on static prompt structures and limited adaptability to complex scenarios remains a major challenge. In this paper, we propose the **Deductive and Inductive (DID)** method, a novel framework…
Video highlight detection is important for video understanding, as it localizes the attractive regions in the video automatically. Because the fully-supervised video highlight is expensive for its frame-level annotation, we present a novel network for weakly-supervised video highlight detection base…
Binocular 3D human pose estimation (HPE), reconstructing a 3D pose from 2D poses of two views, offers practical advantages by combining multiview geometry with the convenience of a monocular setup. However, compared to a multiview setup, the reduction in the number of cameras increases uncertainty i…
Network Pruning is a promising way to address the huge computing resource demands of the deployment and inference of Large Language Models (LLMs). Retraining-free is important for LLMs' pruning methods. However, almost all of the existing retraining-free pruning approaches for LLMs focus on unstruct…
Feature matching is a crucial task in the field of computer vision which involves finding correspondences between images. Previous studies achieve remarkable performance using learning-based feature comparison. However the pervasive presence of matching redundancy between images gives rise to unnece…
In an autonomous driving system, recovering the moving trajectories of the road users and predicting their future trend can greatly assist further driving decision-making. However, there are still many difficulties to solve this problem, due to the insufficient accuracy of the sensors and occlusion
Boundary localization is a challenging problem in Temporal Action Detection (TAD), in which there are two main issues. First, the submergence of movement feature, i.e. the movement information in a snippet is covered by the scene information. Second, the scale of action, that is, the proportion of a…
Breaking down a problem into intermediate steps has demonstrated impressive performance in Large Language Model (LLM) reasoning. However, the growth of the reasoning chain introduces uncertainty and error accumulation, making it challenging to elicit accurate final results. To tackle this challenge…
Background subtraction (BGS) aims to extract all moving objects in the video frames to obtain binary foreground segmentation masks. Deep learning has been widely used in this field. Compared with supervised-based BGS methods, unsupervised methods have better generalization. However, previous unsuper…
Camera calibration is a crucial technique which significantly influences the performance of many robotic systems. Robustness and high precision have always been the pursuit of diverse calibration methods. State-of-the-art calibration techniques, however, still suffer from inexact corner detection, r
Facial expression recognition suffers big pose and occlusion in real world and attention mechanism is deployed widely to cope with these challenges. But most previous attention-based methods are inadequate in locating crucial expression-related regions precisely and capturing useful facial expressio…
Recognizing action patterns and detecting action instances are vital for spatial temporal action detection task, which aims to recognize the actions of interest in untrimmed videos and localize them in both space and time. The mainstream action tubelet detectors, how-ever, ignore the conflicts in fe…
"We propose Structural Triangulation, a closed-form solution for optimal 3D human pose considering multi-view 2D pose estimations, calibrated camera parameters, and bone lengths. To start with, we focus on embedding structural constraints of human body in the process of 2D-to-3D inference using tria…
Although autonomous driving technology has made tremendous progress in recent years, it is still challenging to predict the intentions and trajectories of pedestrians. The state-of-the-art methods suffer from two problems. (1) Existing works consider these two tasks separately, ignoring the connecti…
Temporal action proposal generation is an important yet challenging problem, since temporal proposals with rich action content are indispensable for analysing real-world videos with long duration and high proportion irrelevant content. This problem requires methods not only generating proposals with…
The region-based Convolutional Neural Network (CNN) detectors such as Faster R-CNN or R-FCN have already shown promising results for object detection by combining the region proposal subnetwork and the classification subnetwork together. Although R-FCN has achieved higher detection speed while keepi…