Related papers: Coarse-to-fine Alignment Makes Better Speech-image…
Medical images like CT and MRI provide detailed information about the internal structure of the body, and identifying key anatomical structures from these images plays a crucial role in clinical workflows. Current methods treat it as a…
Speech LLM-based ASR often struggles with named entities and long-tail words due to strong internal language-model priors. Retrieval-augmented biasing can help, but its effectiveness depends on accurate hotword localization in…
Composed Image Retrieval (CIR) allows users to search target images with a multimodal query, comprising a reference image and a modification text that describes the user's modification demand over the reference image. Nevertheless, due to…
Recent deep learning-based methods for lossy image compression achieve competitive rate-distortion performance through extensive end-to-end training and advanced architectures. However, emerging applications increasingly prioritize semantic…
Monaural speech enhancement (SE) is an ill-posed problem due to the irreversible degradation process. Recent methods to achieve SE tasks rely solely on positive information, e.g., ground-truth speech and speech-relevant features. Different…
Face recognition remains a hot topic in computer vision, and it is challenging to tackle the problem that both the training and testing images are corrupted. In this paper, we propose a novel semi-supervised method based on the theory of…
This paper investigates the problem of recovering missing samples using methods based on sparse representation adapted especially for image signals. Instead of $l_2$-norm or Mean Square Error (MSE), a new perceptual quality measure is used…
Employing a dictionary can efficiently rectify the deviation between the visual prediction and the ground truth in scene text recognition methods. However, the independence of the dictionary on the visual features may lead to incorrect…
Text-motion retrieval aims to learn a semantically aligned latent space between natural language descriptions and 3D human motion skeleton sequences, enabling bidirectional search across the two modalities. Most existing methods use a…
Contrastive Language-Image Pretraining (CLIP) achieves strong generalization in vision-language tasks by aligning images and texts in a shared embedding space. However, recent findings show that CLIP-like models still underutilize…
Text-to-image generative models have made significant advancements in recent years; however, accurately capturing intricate details in textual prompts-such as entity missing, attribute binding errors, and incorrect relationships remains a…
Dense retrieval has become the industry standard in large-scale information retrieval systems due to its high efficiency and competitive accuracy. Its core relies on a coarse-to-fine hierarchical architecture that enables rapid candidate…
Despite rapid advances in speech recognition, current models remain brittle to superficial perturbations to their inputs. Small amounts of noise can destroy the performance of an otherwise state-of-the-art model. To harden models against…
Precise audio-visual synchronization in speech videos is crucial for content quality and viewer comprehension. Existing methods have made significant strides in addressing this challenge through rule-based approaches and end-to-end learning…
When performing data classification over a stream of continuously occurring instances, a key challenge is to develop an open-world classifier that anticipates instances from an unknown class. Studies addressing this problem, typically…
Masked image modeling (MIM) learns representations with remarkably good fine-tuning performances, overshadowing previous prevalent pre-training approaches such as image classification, instance contrastive learning, and image-text…
This paper addresses text-supervised semantic segmentation, aiming to learn a model capable of segmenting arbitrary visual concepts within images by using only image-text pairs without dense annotations. Existing methods have demonstrated…
The goal of self-supervised learning (SSL) for automatic speech recognition (ASR) is to learn good speech representations from a large amount of unlabeled speech for the downstream ASR task. However, most SSL frameworks do not consider…
Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases. Given the promising performance contrastive learning has shown recently in…
Dense retrieval conducts text retrieval in the embedding space and has shown many advantages compared to sparse retrieval. Existing dense retrievers optimize representations of queries and documents with contrastive training and map them to…