20 accepted papers
Associative memory has long underpinned the design of sequential models. Beyond recall, humans reason by *projecting future states and selecting goal-directed actions*, a capability that modern language models increasingly require but do not natively encode. While prior work uses reinforcement learn…
Unified audio--visual generation is rapidly gaining industrial and creative relevance, enabling applications in virtual production and interactive media. However, when moving from general audio--video synthesis to music–dance co-generation, the task becomes substantially harder: musical rhythm, phra…
Cued Speech (CS) enhances lipreading via hand coding, offering visual phonemic cues that support precise speech perception for the hearing-impaired. The task of CS Video-to-Speech generation (CSV2S) aims to convert CS videos into intelligible speech signals. Most existing research focuses on CS Reco
Controlling text-to-speech (TTS) systems to synthesize speech with the prosodic characteristics expected by users has attracted much attention. To achieve controllability, current studies focus on two main directions: (1) using reference speech as prosody prompt to guide speech synthesis, and (2) us…
Knowledge distillation for large language models often uses Chain-of-Thought (CoT) and answer pairs, but existing methods struggle with appropriate supervision signals. Uniform constraints (e.g., cross-entropy) on CoT can enforce literal, verbose reasoning and suppress expressive diversity, while so
Camera relocalization is pivotal in computer vision, with applications in AR, drones, robotics, and autonomous driving. It estimates 3D camera position and orientation (6-DoF) from images. Unlike traditional methods like SLAM, recent strides use deep learning for direct end-to-end pose estimation. W…
Knowledge Graph Reasoning aims to derive new insights from existing Knowledge Graphs (KGs) and address any missing or incomplete data. Existing models primarily rely on explicit information while neglecting the implicit constraints imposed by entity types on relations types. For example, when the en…
Scene-aware Complementary Item Retrieval (CIR) is a challenging task which requires to generate a set of compatible items across domains. Due to the subjectivity, it is difficult to set up a rigorous standard for both data collection and learning objectives. To address this challenging task, we prop…
Recent research in zero-shot Relation Extraction (RE) has focused on using Large Language Models (LLMs) due to their impressive zero-shot capabilities. However, current methods often perform suboptimally, mainly due to a lack of detailed, context-specific prompts needed for understanding various sen…
"We propose an efficient Video-Language Alignment (ViLA) network. Our ViLA model addresses both efficient frame sampling and effective cross-modal alignment in a unified way. In our ViLA network, we design a new learnable text-guided Frame-Prompter together with a cross-modal distillation (QFormer-D…
Text-to-speech (TTS) and singing voice synthesis (SVS) aim at generating high-quality speaking and singing voice according to textual input and music scores, respectively. Unifying TTS and SVS into a single system is crucial to the applications requiring both of them. Existing methods usually suffer…
Cross-speaker style transfer (CSST) in text-to-speech (TTS) synthesis aims at transferring a speaking style to the synthesised speech in a target speaker’s voice. Most previous CSST approaches rely on expensive high-quality data carrying desired speaking style during training and require a re…
Though significant progress has been made for speaker-dependent Video-to-Speech (VTS) synthesis, little attention is devoted to multi-speaker VTS that can map silent video to speech, while allowing flexible control of speaker identity, all in a single system. This paper proposes a novel multi-speake…
We present AIST++, a new multi-modal dataset of 3D dance motion and music, along with FACT, a Full-Attention Cross-modal Transformer network for generating 3D dance motion conditioned on music. The proposed AIST++ dataset contains 1.1M frames of 3D dance motion in 1408 sequences, covering 10 dance g…
Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio. Machine perception models, in stark contrast, are typically modality-specific and optimised for unimodal benchmarks. A common approach for building multimodal m…
Few-shot relation extraction (FSRE) is of great importance in long-tail distribution problem, especially in special domain with low-resource data. Most existing FSRE algorithms fail to accurately classify the relations merely based on the information of the sentences together with the recognized ent…
In this paper, we aim to recognize materials with combined use of auditory and visual perception. To this end, we construct a new dataset named GLAudio that consists of both the geometry of the object being struck and the sound captured from either modal sound synthesis (for virtual objects) or real…
Compared with the conventional "front-end"-"back-end"- "vocoder" structure, based on the attention mechanism, end-to-end speech synthesis systems directly train and synthesize from text sequence to the acoustic feature sequence as a whole. Recently, a more calculation efficient end-to-end architectu…
Image understanding enables better reconstruction of the physical world from images and videos. Existing methods focus largely on geometry and visual appearance of the reconstructed scene. In this paper, we extend the frontier in image understanding and present a new technique to recover the materia…
Material property has great importance in medical robotics. The mechanical properties of the human soft tissue, are important to characterize the tissue deformation of each patient. The (recovered) elasticity parameters can assist surgeons to perform better pre-op surgical planning and enable medica