19 accepted papers
As an important branch of unsupervised learning, deep clustering has seen substantial progress in recent years. However, the majority of current deep clustering methods operate under the assumption of balanced or near-balanced cluster distributions. This assumption contradicts the common long-tailed…
Low-light images are commonly present due to imaging factors such as insufficient light, night shooting and back lit. Existing low-light image enhancement (LLIE) methods typically rely on a low-light input image for enhancement, which seldom leverage information contained in its high-light counterpa…
Deep clustering has made remarkable progress in recent years. However, most existing deep clustering methods assume that distributions of different clusters are balanced or roughly balanced, which are not consistent with the common long-tailed distributions in reality. In nature, the datasets often…
Large Language Models (LLMs) aligned with human feedback have recently garnered significant attention. However, it remains vulnerable to jailbreak attacks, where adversaries manipulate prompts to induce harmful outputs. Exploring jailbreak attacks enables us to investigate the vulnerabilities of LLM…
Deep clustering, an unsupervised technique independent of labels, necessitates tailored supervision for model training. Prior methods explore supervision like similarity and pseudo labels, yet overlook individual sample training analysis. Our study correlates sample stability during unsupervised tra…
Low-light image enhancement (LLIE) can be reformulated as an image-specific curve estimation (CE) problem. Traditional CE-based methods struggle with issues such as uniform processing across different regions, static parameter estimation, and lack of effective global semantic enhancement. To address…
Text-based Person Search is one of the downstream tasks of cross-modal retrieval. The key challenge is aligning features of two extremely irrelavant modalities into the same latent space. Recent works within Prototype Learning introduce a few learnable parameters to map heterogeneous features into t…
Recent research ideas mainly focus on solving the semantic consistency of visual features and label features. However, since images contain complex scene content, the features captured by visual feature extraction networks based on grid or sequence representation may introduce redundant information…
Prompt learning was proposed to solve the problem of inconsistency between the upstream and downstream tasks and has achieved State-Of-The-Art (SOTA) results in various Natural Language Processing (NLP) tasks. However, Relation Extraction (RE) is more complex than other text classification tasks, wh…
Most existing transformer-based trackers use ViT [1] as the backbone to extract and fuse feature tokens of target templates and search region. Since both the target template and the search region contain background information, their tokens are prone to background interference in interaction that af…
Rich image and text features can largely improve the training of image captioning tasks. However, rich image and text features mean the incorporation of a large amount of unnecessary information. In our work, in order to fully explore and utilize the key information in images and text, we view the c…
Despite the advances in Visual Question Answering (VQA), many VQA models currently suffer from language priors (i.e. generating answers directly from questions without using images), which severely reduces their robustness in real-world scenarios. We propose a novel training strategy called Loss Reb…
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 target movement, and attraction from similar objects. To al…
In recent years, image caption methods based on the encoder-decoder framework have made promising achievements, but most of them lack the exploitation of global information. In general, visual global information can provide more fine-grain details for recognizing small objects. On the other hand, th…
Cross-modal retrieval relies on learning inter-modal correspondences. Most existing approaches focus on learning global or local correspondence and fail to explore fine-grained multi-level alignments. Moreover, it remains to be investigated how to infer more accurate similarity scores. In this paper…
The performance of image captioning has been significantly improved recently through deep neural network architectures combining with attention mechanisms and reinforcement learning optimization. Exploring visual relationships and interactions between different objects appearing in the image, howeve…
Internal relationship of image objects has contributed significantly to the development of image captioning, especially when combined with Transformer architecture. Most of these methods only calculate the relationship between entities and ignore the information between entities and background. Besi…
Person attribute or pose information has improved person re-identification performance, however, inaccurate pose or attribute module will damage the final identification performance. Based on this, we propose a multi-scale relation aware network (MSRA) for person re-identification. Specifically, we…
The convolution operation suffers from a limited receptive field, while global modeling is fundamental to dense prediction tasks, such as semantic segmentation. However, most existing methods treat the recognition of each region separately and overlook crucial global semantic relations between regio…