相关论文: GranAlign: Granularity-Aware Alignment Framework f…

The current state-of-the-art methods for video corpus moment retrieval (VCMR) often use similarity-based feature alignment approach for the sake of convenience and speed. However, late fusion methods like cosine similarity alignment are…

Long-range temporal alignment is critical yet challenging for video restoration tasks. Recently, some works attempt to divide the long-range alignment into several sub-alignments and handle them progressively. Although this operation is…

Recent progress in large-scale pre-training has led to the development of advanced vision-language models (VLMs) with remarkable proficiency in comprehending and generating multimodal content. Despite the impressive ability to perform…

Temporal Video Grounding (TVG) aims to localize a moment from an untrimmed video given the language description. Since the annotation of TVG is labor-intensive, TVG under limited supervision has accepted attention in recent years. The great…

The goal of video moment retrieval and highlight detection is to identify specific segments and highlights based on a given text query. With the rapid growth of video content and the overlap between these tasks, recent works have addressed…

Large Vision Language Models (LVLMs) have demonstrated impressive zero-shot capabilities in various vision-language dialogue scenarios. However, the absence of fine-grained visual object detection hinders the model from understanding the…

Generalization to unseen tasks is an important ability for few-shot learners to achieve better zero-/few-shot performance on diverse tasks. However, such generalization to vision-language tasks including grounding and generation tasks has…

Prevailing joint prediction transformers for Video Highlight Detection and Moment Retrieval (HD/MR) exhibit deficiencies in handling cross-task dynamics, achieving robust video-text alignment, and utilizing effective attention mechanisms,…

Vision-language models (VLMs) have demonstrated remarkable performance across various visual tasks, leveraging joint learning of visual and textual representations. While these models excel in zero-shot image tasks, their application to…

The rocketing prosperity of large language models (LLMs) in recent years has boosted the prevalence of vision-language models (VLMs) in the medical sector. In our online medical consultation scenario, a doctor responds to the texts and…

Retrieving molecular structures from tandem mass spectra is a crucial step in rapid compound identification. Existing retrieval methods, such as traditional mass spectral library matching, suffer from limited spectral library coverage,…

Recent motion-language models unify tasks like comprehension and generation but operate at a coarse granularity, lacking fine-grained understanding and nuanced control over body parts needed for animation or interaction. This stems from…

We propose VideoPerceiver, a novel video multimodal large language model (VMLLM) that enhances fine-grained perception in video understanding, addressing VMLLMs' limited ability to reason about brief actions in short clips or rare transient…

Understanding and reasoning over long videos pose significant challenges for large video language models (LVLMs) due to the difficulty in processing intensive video tokens beyond context window and retaining long-term sequential…

Video editing and synthesis often introduce object inconsistencies, such as frame flicker and identity drift that degrade perceptual quality. To address these issues, we introduce ObjectAlign, a novel framework that seamlessly blends…

Ensuring cultural values alignment in Large Language Models (LLMs) remains a critical challenge, as these models often embed Western-centric biases from their training data, leading to misrepresentations and fairness concerns in…

Zero-shot visual question answering (ZS-VQA), an emerged critical research area, intends to answer visual questions without providing training samples. Existing research in ZS-VQA has proposed to leverage knowledge graphs or large language…

Video recognition in an open and dynamic world is quite challenging, as we need to handle different settings such as close-set, long-tail, few-shot and open-set. By leveraging semantic knowledge from noisy text descriptions crawled from the…

Generative vision-language models (VLMs) exhibit strong high-level image understanding but lack spatially dense alignment between vision and language modalities, as our findings indicate. Orthogonal to advancements in generative VLMs,…

We present an audio-visual multimodal approach for the task of zeroshot learning (ZSL) for classification and retrieval of videos. ZSL has been studied extensively in the recent past but has primarily been limited to visual modality and to…