Related papers: StyleDubber: Towards Multi-Scale Style Learning fo…
Contemporary Vision-Language Models (VLMs) achieve strong performance on a wide range of tasks by pairing a vision encoder with a pre-trained language model, fine-tuned for visual-text inputs. Yet despite these gains, it remains unclear how…
In this paper, we address the task of multimodal-to-speech generation, which aims to synthesize high-quality speech from multiple input modalities: text, video, and reference audio. This task has gained increasing attention due to its wide…
Understanding social interaction in video requires reasoning over a dynamic interplay of verbal and non-verbal cues: who is speaking, to whom, and with what gaze or gestures. While Multimodal Large Language Models (MLLMs) are natural…
Creating realistic or stylized facial and lip sync animation is a tedious task. It requires lot of time and skills to sync the lips with audio and convey the right emotion to the character's face. To allow animators to spend more time on…
Controllable speech synthesis aims to control the style of generated speech using reference input, which can be of various modalities. Existing face-based methods struggle with robustness and generalization due to data quality constraints,…
Vivid talking face generation holds immense potential applications across diverse multimedia domains, such as film and game production. While existing methods accurately synchronize lip movements with input audio, they typically ignore…
Audio-driven 3D facial animation has several virtual humans applications for content creation and editing. While several existing methods provide solutions for speech-driven animation, precise control over content (what) and style (how) of…
This study aims to explore efficient tuning methods for the screenshot captioning task. Recently, image captioning has seen significant advancements, but research in captioning tasks for mobile screens remains relatively scarce. Current…
Rapid development of large language models (LLMs) has significantly advanced multimodal large language models (LMMs), particularly in vision-language tasks. However, existing video-language models often overlook precise temporal…
Audiovisual representation learning typically relies on the correspondence between sight and sound. However, there are often multiple audio tracks that can correspond with a visual scene. Consider, for example, different conversations on…
Speech-driven talking face synthesis (TFS) focuses on generating lifelike facial animations from audio input. Current TFS models perform well in English but unsatisfactorily in non-English languages, producing wrong mouth shapes and rigid…
The remarkable potential of multi-modal large language models (MLLMs) in comprehending both vision and language information has been widely acknowledged. However, the scarcity of 3D scenes-language pairs in comparison to their 2D…
Systems that can find correspondences between multiple modalities, such as between speech and images, have great potential to solve different recognition and data analysis tasks in an unsupervised manner. This work studies multimodal…
We propose a novel approach for multi-modal Image-to-image (I2I) translation. To tackle the one-to-many relationship between input and output domains, previous works use complex training objectives to learn a latent embedding, jointly with…
Temporal Video Grounding (TVG) aims to localize the temporal boundary of a specific segment in an untrimmed video based on a given language query. Since datasets in this domain are often gathered from limited video scenes, models tend to…
Concept Bottleneck Models (CBMs) offer inherent interpretability by initially translating images into human-comprehensible concepts, followed by a linear combination of these concepts for classification. However, the annotation of concepts…
End-to-end audio-conditioned latent diffusion models (LDMs) have been widely adopted for audio-driven portrait animation, demonstrating their effectiveness in generating lifelike and high-resolution talking videos. However, direct…
In this study, we address the multimodal task of stereo sound event localization and detection with source distance estimation (3D SELD) in regular video content. 3D SELD is a complex task that combines temporal event classification with…
Vision-language models bridge visual and linguistic understanding and have proven to be powerful for video recognition tasks. Existing approaches primarily rely on parameter-efficient fine-tuning of image-text pre-trained models, yet they…
The Contrastive Language-Image Pre-training (CLIP) framework has become a widely used approach for multimodal representation learning, particularly in image-text retrieval and clustering. However, its efficacy is constrained by three key…