相关论文: Alleviating Merge Conflicts with Fine-grained Visu…
The Audio-Visual Video Parsing task aims to recognize and temporally localize all events occurring in either the audio or visual stream, or both. Capturing accurate event semantics for each audio/visual segment is vital. Prior works…
In e-commerce, product content, especially product images have a significant influence on a customer's journey from product discovery to evaluation and finally, purchase decision. Since many e-commerce retailers sell items from other…
Manipulating images of complex scenes to reconstruct, insert and/or remove specific object instances is a challenging task. Complex scenes contain multiple semantics and objects, which are frequently cluttered or ambiguous, thus hampering…
Establishing reliable image correspondences is essential for many robotic vision problems. However, existing methods often struggle in challenging scenarios with large viewpoint changes or textureless regions, where incorrect cor-…
Large-scale contrastive pre-training produces powerful Vision-and-Language Models (VLMs) capable of generating representations (embeddings) effective for a wide variety of visual and multimodal tasks. However, these pretrained embeddings…
Graph-based representations such as Scene Graphs enable localization in structured indoor environments by matching a locally observed graph, constructed from sensor data, to a prior map. This process is particularly challenging in…
Large-scale companies commonly face the challenge of managing relevant knowledge between different organizational groups, particularly in increasingly agile contexts. In previous studies, we found the importance of analyzing methodological…
While some work attempt to generate front-end code intelligently from UI screenshots, it may be more convenient to utilize UI design drafts in Sketch which is a popular UI design software, because we can access multimodal UI information…
In view of the problems that existing salient object detection (SOD) methods are prone to losing details, blurring edges, and insufficient fusion of single-modal information in complex scenes, this paper proposes a dynamic uncertainty…
Online semantic 3D segmentation in company with real-time RGB-D reconstruction poses special challenges such as how to perform 3D convolution directly over the progressively fused 3D geometric data, and how to smartly fuse information from…
The vulnerability of Deep Neural Networks to adversarial perturbations presents significant security concerns, as the imperceptible perturbations can contaminate the feature space and lead to incorrect predictions. Recent studies have…
Communication overhead has become one of the major bottlenecks in the distributed training of deep neural networks. To alleviate the concern, various gradient compression methods have been proposed, and sign-based algorithms are of surging…
Developing an algorithm for a visualization prototype often involves the direct comparison of different development stages and design decisions, and even minor modifications may dramatically affect the results. While existing development…
Ultra-high resolution image segmentation has raised increasing interests in recent years due to its realistic applications. In this paper, we innovate the widely used high-resolution image segmentation pipeline, in which an ultra-high…
In this study, we explore advanced strategies for enhancing software quality by detecting and refactoring data clumps, special types of code smells. Our approach transcends the capabilities of integrated development environments, utilizing…
Group-level emotion recognition (GER) aims to identify holistic emotions within a scene involving multiple individuals. Current existed methods underestimate the importance of visual scene contextual information in modeling individual…
Code comments play a crucial role in software development, as they provide programmers with practical information, allowing them to understand better the intent and semantics of the underpinning code. Nevertheless, developers tend to leave…
Emotion recognition in multi-speaker conversations faces significant challenges due to speaker ambiguity and severe class imbalance. We propose a novel framework that addresses these issues through three key innovations: (1) a speaker…
As Generative Engines revolutionize information retrieval by synthesizing direct answers from retrieved sources, ensuring source visibility becomes a significant challenge. Improving it through targeted content revisions is a practical…
Model merging is an effective strategy to merge multiple models for enhancing model performances, and more efficient than ensemble learning as it will not introduce extra computation into inference. However, limited research explores if the…