相关论文: CLIP-Powered TASS: Target-Aware Single-Stream Netw…

While Test-Time Scaling (TTS) offers a promising direction to enhance video generation without the surging costs of training, current test-time video generation methods based on diffusion models suffer from exorbitant candidate exploration…

Video Question Answering (VQA) requires models to reason over spatial, temporal, and causal cues in videos. Recent vision language models (VLMs) achieve strong results but often rely on shallow correlations, leading to weak temporal…

In recent years, advancements in representation learning and language models have propelled Automated Captioning (AC) to new heights, enabling the generation of human-level descriptions. Leveraging these advancements, we propose AVCap, an…

This work explores text-to-image retrieval for queries that specify or describe a semantic category. While vision-and-language models (VLMs) like CLIP offer a straightforward open-vocabulary solution, they map text and images to distant…

Recent advancements in language-model-based video understanding have been progressing at a remarkable pace, spurred by the introduction of Large Language Models (LLMs). However, the focus of prior research has been predominantly on devising…

Recent Large Vision Language Models (LVLMs) demonstrate promising capabilities in unifying visual understanding and generative modeling, enabling both accurate content understanding and flexible editing. However, current approaches treat…

Audio-visual approaches involving visual inputs have laid the foundation for recent progress in speech separation. However, the optimization of the concurrent usage of auditory and visual inputs is still an active research area. Inspired by…

Vision-language pre-training (VLP) on large-scale image-text pairs has recently witnessed rapid progress for learning cross-modal representations. Existing pre-training methods either directly concatenate image representation and text…

In recent years, the growing demand for medical imaging diagnosis has placed a significant burden on radiologists. As a solution, Medical Vision-Language Pre-training (Med-VLP) methods have been proposed to learn universal representations…

Video-and-language pre-training has shown promising improvements on various downstream tasks. Most previous methods capture cross-modal interactions with a transformer-based multimodal encoder, not fully addressing the misalignment between…

Vision-language pre-training (VLP) methods are blossoming recently, and its crucial goal is to jointly learn visual and textual features via a transformer-based architecture, demonstrating promising improvements on a variety of…

Multi-Agent Systems (MAS) powered by Large Language Models have unlocked advanced collaborative reasoning, yet they remain bottlenecked by discrete text communication, which imposes runtime overhead and information quantization loss. While…

Vision-Language Models (VLMs) such as CLIP demonstrate strong zero-shot generalization, but their performance significantly degrades in cross-domain scenarios with scarce target-domain training data (Cross-Domain Few-Shot Learning, CDFSL).…

Class Activation Map (CAM) has emerged as a popular tool for weakly supervised semantic segmentation (WSSS), allowing the localization of object regions in an image using only image-level labels. However, existing CAM methods suffer from…

The landscape of publicly available vision foundation models (VFMs), such as CLIP and Segment Anything Model (SAM), is expanding rapidly. VFMs are endowed with distinct capabilities stemming from their pre-training objectives. For instance,…

Open-vocabulary semantic segmentation (OVSS) is fundamentally hampered by the coarse, image-level representations of CLIP, which lack precise pixel-level details. Existing training-free methods attempt to resolve this by either importing…

With the flourishing of social media platforms, vision-language pre-training (VLP) recently has received great attention and many remarkable progresses have been achieved. The success of VLP largely benefits from the information…

Machine Interpreting systems are currently implemented as unimodal, real-time speech-to-speech architectures, processing translation exclusively on the basis of the linguistic signal. Such reliance on a single modality, however, constrains…

The recently proposed visually grounded speech model SpeechCLIP is an innovative framework that bridges speech and text through images via CLIP without relying on text transcription. On this basis, this paper introduces two extensions to…

The advancement of Multimodal Large Language Models (MLLMs) has driven significant progress in Visual Question Answering (VQA), evolving from Single to Multi Image VQA (MVQA). However, the increased number of images in MVQA inevitably…