Related papers: CLIP-Powered TASS: Target-Aware Single-Stream Netw…
Video dubbing aims to generate high-fidelity speech that is precisely temporally aligned with the visual content. Existing methods still suffer from limitations in speech naturalness and audio-visual synchronization, and are limited to…
Audio-Visual Question Answering (AVQA) requires not only question-based multimodal reasoning but also precise temporal grounding to capture subtle dynamics for accurate prediction. However, existing methods mainly use question information…
This paper presents a unified Vision-Language Pre-training (VLP) model. The model is unified in that (1) it can be fine-tuned for either vision-language generation (e.g., image captioning) or understanding (e.g., visual question answering)…
Audio and visual signals typically occur simultaneously, and humans possess an innate ability to correlate and synchronize information from these two modalities. Recently, a challenging problem known as Audio-Visual Segmentation (AVS) has…
Large-scale single-stream pre-training has shown dramatic performance in image-text retrieval. Regrettably, it faces low inference efficiency due to heavy attention layers. Recently, two-stream methods like CLIP and ALIGN with high…
Vision-language models (VLMs), such as CLIP, have demonstrated strong performance across a range of downstream tasks. However, CLIP is still limited in negation understanding: the ability to recognize the absence or exclusion of a concept.…
Vision-language tasks, such as VQA, SNLI-VE, and VCR are challenging because they require the model's reasoning ability to understand the semantics of the visual world and natural language. Supervised methods working for vision-language…
The recent advancements in Generative Adversarial Networks (GANs) and the emergence of Diffusion models have significantly streamlined the production of highly realistic and widely accessible synthetic content. As a result, there is a…
Vision-language alignment learning for video-text retrieval arouses a lot of attention in recent years. Most of the existing methods either transfer the knowledge of image-text pretraining model to video-text retrieval task without fully…
Audio-visual semantic segmentation (AVSS) represents an extension of the audio-visual segmentation (AVS) task, necessitating a semantic understanding of audio-visual scenes beyond merely identifying sound-emitting objects at the visual…
Text-to-video retrieval requires precise alignment between language and temporally rich audio-video signals. However, existing methods often emphasize visual cues while underutilizing audio semantics or relying on coarse fusion strategies,…
Remote sensing image-text retrieval plays a crucial role in remote sensing interpretation, yet remains challenging under both closed-domain and open-domain scenarios due to semantic noise and domain shifts. To address these issues, we…
The large-scale pretrained model CLIP, trained on 400 million image-text pairs, offers a promising paradigm for tackling vision tasks, albeit at the image level. Later works, such as DenseCLIP and LSeg, extend this paradigm to dense…
Research on multi-modal contrastive learning strategies for audio and text has rapidly gained interest. Contrastively trained Audio-Language Models (ALMs), such as CLAP, which establish a unified representation across audio and language…
Audio-Visual Segmentation (AVS) aims to segment sound-producing objects in video frames based on the associated audio signal. Prevailing AVS methods typically adopt an audio-centric Transformer architecture, where object queries are derived…
While large audio-language models (LALMs) have demonstrated state-of-the-art audio understanding, their reasoning capability in complex soundscapes still falls behind large vision-language models (LVLMs). Compared to the visual domain, one…
In recent years, numerous tasks have been proposed to encourage model to develop specified capability in understanding audio-visual scene, primarily categorized into temporal localization, spatial localization, spatio-temporal reasoning,…
Visual Grounding (VG) is a crucial topic in the field of vision and language, which involves locating a specific region described by expressions within an image. To reduce the reliance on manually labeled data, unsupervised visual grounding…
Vision-language models (VLMs) are commonly trained by directly inserting image tokens from a pretrained vision encoder into the text stream of a language model. This allows text and image information to fully attend to one another within…
Text-driven image manipulation is developed since the vision-language model (CLIP) has been proposed. Previous work has adopted CLIP to design a text-image consistency-based objective to address this issue. However, these methods require…