相关论文: More Than Meets the Eye: A Semantics-Aware Traffic…

With the evolution of 6G, semantic communication has emerged as a promising paradigm by prioritizing the delivery of task-relevant meaning over strict bit-level correctness. However, existing transport mechanisms still rely on explicit port…

Most deep trackers still follow the guidance of the siamese paradigms and use a template that contains only the target without any contextual information, which makes it difficult for the tracker to cope with large appearance changes, rapid…

Pedestrian attribute recognition (PAR) is a fundamental perception task in intelligent transportation and security. To tackle this fine-grained task, most existing methods focus on extracting regional features to enrich attribute…

Deep features extracted from certain layers of a pre-trained deep model show superior performance over the conventional hand-crafted features. Compared with fine-tuning or linear probing that can explore diverse augmentations, \eg, random…

In deep learning for drug discovery, chemical data are often represented as simplified molecular-input line-entry system (SMILES) sequences which allow for straightforward implementation of natural language processing methodologies, one…

Driver attention prediction is becoming an essential research problem in human-like driving systems. This work makes an attempt to predict the driver attention in driving accident scenarios (DADA). However, challenges tread on the heels of…

Graph-based learning excels at capturing interaction patterns in diverse domains like recommendation, fraud detection, and particle physics. However, its performance often degrades under distribution shifts, especially those altering…

Analyzing flight trajectory data sets poses challenges due to the intricate interconnections among various factors and the high dimensionality of the data. Topological Data Analysis (TDA) is a way of analyzing big data sets focusing on the…

Transparent object perception remains a major challenge in computer vision research, as transparency confounds both depth estimation and semantic segmentation. Recent work has explored multi-task learning frameworks to improve robustness,…

Wearable human activity recognition (WHAR) models often suffer from performance degradation under real-world cross-user distribution shifts. Test-time adaptation (TTA) mitigates this degradation by adapting models online using unlabeled…

In modern urban environments, camera networks generate massive amounts of operational footage -- reaching petabytes each day -- making scalable video analytics essential for efficient processing. Many existing approaches adopt an SQL-based…

Using synthetic data for training neural networks that achieve good performance on real-world data is an important task as it can reduce the need for costly data annotation. Yet, synthetic and real world data have a domain gap. Reducing…

Understanding 3D scene-level affordances from natural language instructions is essential for enabling embodied agents to interact meaningfully in complex environments. However, this task remains challenging due to the need for semantic…

We present a real-time semantic mapping approach for mobile vision systems with a 2D to 3D object detection pipeline and rapid data association for generated landmarks. Besides the semantic map enrichment the associated detections are…

Large language models (LLMs) demonstrate strong task-specific capabilities through fine-tuning, but merging multiple fine-tuned models often leads to degraded performance due to overlapping instruction-following components. Task Arithmetic…

Synthetically augmenting training datasets with diffusion models has become an effective strategy for improving the generalization of image classifiers. However, existing approaches typically increase dataset size by 10-30x and struggle to…

To perform outdoor visual navigation and search, a robot may leverage satellite imagery to generate visual priors. This can help inform high-level search strategies, even when such images lack sufficient resolution for target recognition.…

Recently unpaired multi-domain image-to-image translation has attracted great interests and obtained remarkable progress, where a label vector is utilized to indicate multi-domain information. In this paper, we propose SAT (Show, Attend and…

Test-time adaptive (TTA) semantic segmentation adapts a source pre-trained image semantic segmentation model to unlabeled batches of target domain test images, different from real-world, where samples arrive one-by-one in an online fashion.…

Unsupervised domain adaptation (UDA) aims to transfer and adapt knowledge from a labeled source domain to an unlabeled target domain. Traditionally, subspace-based methods form an important class of solutions to this problem. Despite their…