相关论文: LaSTR: Language-Driven Time-Series Segment Retriev…

We address the task of video chaptering, i.e., partitioning a long video timeline into semantic units and generating corresponding chapter titles. While relatively underexplored, automatic chaptering has the potential to enable efficient…

Recent advancement in large language models (LLMs) has offered a strong potential for natural language systems to process informal language. A representative form of informal language is slang, used commonly in daily conversations and…

We look at the long-standing problem of segmenting unlabeled speech into word-like segments and clustering these into a lexicon. Several previous methods use a scoring model coupled with dynamic programming to find an optimal segmentation.…

Text--image retrieval is necessary for applications such as product recommendation. Embedding-based approaches like CLIP enable efficient large-scale retrieval via vector similarity search, but they are primarily trained on literal…

Scene text recognition (STR) has been an active research topic in computer vision for years. To tackle this challenging problem, numerous innovative methods have been successively proposed and incorporating linguistic knowledge into STR…

Cross-modal retrieval (CMR) has been extensively applied in various domains, such as multimedia search engines and recommendation systems. Most existing CMR methods focus on image-to-text retrieval, whereas audio-to-text retrieval, a less…

Referring image segmentation is an advanced semantic segmentation task where target is not a predefined class but is described in natural language. Most of existing methods for this task rely heavily on convolutional neural networks, which…

Scene text detection task has attracted considerable attention in computer vision because of its wide application. In recent years, many researchers have introduced methods of semantic segmentation into the task of scene text detection, and…

Pre-trained vision-language models~(VLMs) are the de-facto foundation models for various downstream tasks. However, scene text recognition methods still prefer backbones pre-trained on a single modality, namely, the visual modality, despite…

This paper presents an improved framework for character-aware audio-visual subtitling in TV shows. Our approach integrates speech recognition, speaker diarisation, and character recognition, utilising both audio and visual cues. This…

Vision-language models like CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions because of their training focus on short and concise captions. We present…

Existing retrieval methods in Large Language Models show degradation in accuracy when handling temporally distributed conversations, primarily due to their reliance on simple similarity-based retrieval. Unlike existing memory retrieval…

Referring Video Object Segmentation (RVOS) aims to segment target objects in videos based on natural language descriptions. However, fixed keyframe-based approaches that couple a vision language model with a separate propagation module…

Click-Through Rate (CTR) prediction is crucial for Recommendation System(RS), aiming to provide personalized recommendation services for users in many aspects such as food delivery, e-commerce and so on. However, traditional RS relies on…

The task of retrieving clips within videos based on a given natural language query requires cross-modal reasoning over multiple frames. Prior approaches such as sliding window classifiers are inefficient, while text-clip similarity driven…

Deep neural networks for time series must capture complex temporal patterns, to effectively represent dynamic data. Self- and semi-supervised learning methods show promising results in pre-training large models, which -- when finetuned for…

Fine-grained category discovery using only coarse-grained supervision is a cost-effective yet challenging task. Previous training methods focus on aligning query samples with positive samples and distancing them from negatives. They often…

Combining Large Language Models (LLMs) with heuristic search algorithms like A* holds the promise of enhanced LLM reasoning and scalable inference. To accelerate training and reduce computational demands, we investigate the coreset…

More and more neural network approaches have achieved considerable improvement upon submodules of speaker diarization system, including speaker change detection and segment-wise speaker embedding extraction. Still, in the clustering stage,…

While speech large language models (SpeechLLMs) have advanced standard automatic speech recognition (ASR), contextual biasing for named entities and rare words remains challenging, especially at scale. To address this, we propose BR-ASR: a…