65 accepted papers
Pixel diffusion aims to generate images directly in pixel space in an end-to-end fashion. This approach avoids the limitations of VAE in the two-stage latent diffusion, offering higher model capacity. Existing pixel diffusion models suffer from slow training and inference, as they usually model both
Existing video generation models predominantly emphasize appearance fidelity while exhibiting limited ability to synthesize complex human motions, such as whole-body movements, long-range dynamics, and fine-grained human–environment interactions. This often leads to unrealistic or physically implaus…
Lifelong person re-identification (LReID) aims to train a generalizable model with sequentially collected data. However, such models often suffer from semantic drift, limited adaptability, and catastrophic forgetting as new domains emerge. Existing exemplar-free approaches largely rely on visual-onl
Human artists can continuously refine their coarse sketches during artistic creation. This is quite different from existing autoregressive generation, where a token is determined once sampled. Aiming to flexibly refine the generated contents, this paper presents a Self-Calibrated AutoregressioN (SCA
Existing adversarial attacks on large Vision-Language Models (VLMs) often struggle with limited transferability to black-box models or produce perceptible artifacts that are easily detected. This paper presents Progressive Semantic Infusion (PSI), a diffusion-based attack that progressively aligns a…
Recent researchers have proposed using event cameras for person re-identification (ReID) due to their promising performance and better balance in terms of privacy protection, event camera-based person ReID has attracted significant attention. Currently, mainstream event-based person ReID algorithms
We introduce 3D-Speaker-Toolkit, an open-source toolkit for multimodal speaker verification and diarization, designed for meeting the needs of academic researchers and industrial practitioners. The 3D-Speaker-Toolkit adeptly leverages the combined strengths of acoustic, semantic, and visual data, se…
Traditional approaches to adapting multi-modal large language models (MLLMs) to new tasks have relied heavily on fine-tuning. This paper introduces Efficient Multi-Modal Long Context Learning (EMLoC), a novel training-free alternative that embeds demonstration examples directly into the model input.…
While automatic speech recognition (ASR) systems have achieved remarkable performance with large-scale datasets, their efficacy remains inadequate in low-resource settings, encompassing dialects, accents, minority languages, and long-tail hotwords, domains with significant practical relevance. With…
Generalizable object keypoint localization is a fundamental computer vision task in understanding the object structure. It is challenging for existing keypoint localization methods because their limited training data cannot provide generalizable shape and semantic cues, leading to inferior performan…
The goal of image-based virtual try-on is to generate an image of the target person naturally wearing the given clothing. However, existing methods solely focus on the frontal try-on using the frontal clothing. When the views of the clothing and person are significantly inconsistent, particularly wh…
Existing acceleration techniques for video diffusion models often rely on uniform heuristics or time-embedding variants to skip timesteps and reuse cached features. These approaches typically require extensive calibration with curated prompts and risk inconsistent outputs due to prompt-specific over…
The growing use of deep learning necessitates efficient network design and deployment, making neural predictors vital for estimating attributes such as accuracy and latency. Recently, Graph Neural Networks (GNNs) and transformers have shown promising performance in representing neural architectures.…
Traditional video-to-audio generation techniques primarily focus on perspective video and non-spatial audio, often missing the spatial cues necessary for accurately representing sound sources in 3D environments. To address this limitation, we introduce a novel task, \textbf{360V2SA}, to generate spa…
Full-duplex spoken dialogue systems significantly surpass traditional turn-based dialogue systems, as they allow simultaneous bidirectional communication, closely mirroring human-human interactions. However, achieving low latency and natural interactions in full-duplex dialogue systems remains a sig…
Training speaker-discriminative and robust speaker verification systems without explicit speaker labels remains a persistent challenge. In this paper, we propose a novel self-supervised speaker verification approach, Self-Distillation Prototypes Network (SDPN), which effectively facilitates self-sup…
In this paper, we focus on prompting one of the most important tasks in the field of speech processing, i.e., automatic speech recognition (ASR), with speech foundation encoders and large language models (LLM). Despite the growing body of research in this area, we find that many crucial design decis…
The emergence of audio language models is empowered by neural audio codecs, which establish critical mappings between continuous waveforms and discrete tokens compatible with language model paradigms. The evolutionary trends from multi-layer residual vector quantizer to single-layer quantizer are be…
While recent advances in reference-based speaker cloning have significantly improved the authenticity of synthetic speech, speaker generation driven by multimodal cues such as visual appearance, textual descriptions, and other biometric signals remains in its early stages. To pioneer truly multimoda
Existing video generation strategies can be categorized into two categories, i.e., the diffusion and autoregressive (AR) methods. While AR methods achieves high efficiency by predicting the next token based on known visual cues, they generally fall short of diffusion models in terms of video quality…
Supervised Contrastive Loss (SCL) is popular in visual representation learning. Given an anchor image, SCL pulls two types of positive samples, i.e., its augmentation and other images from the same class together, while pushes negative images apart to optimize the learned embedding. In the scena…
When training on a long-tailed dataset, conventional learning algorithms tend to exhibit a bias towards classes with a larger sample size. Our investigation has revealed that this biased learning tendency originates from the model parameters, which are trained to disproportionately contribute to the…
This paper presents FunCodec, a fundamental neural speech codec toolkit, which is an extension of the open-source speech processing toolkit FunASR. FunCodec provides reproducible training recipes and inference scripts for the latest neural speech codec models, such as SoundStream and Encodec. Thanks…
Recently audio-visual speech recognition (AVSR), which better leverages video modality as additional information to extend automatic speech recognition (ASR), has shown promising results in complex acoustic environments. However, there is still substantial space to improve as complex computation of…
The growing prevalence of online conferences and courses presents a new challenge in improving automatic speech recognition (ASR) with enriched textual information from video slides. In contrast to rare phrase lists, the slides within videos are synchronized in real-time with the speech, enabling th…
In this paper, we explored how to boost speech emotion recognition (SER) with the state-of-the-art speech pre-trained model (PTM), data2vec, text generation technique, GPT-4, and speech synthesis technique, Azure TTS. First, we investigated the representation ability of different speech self-supervi…
The capacity of existing human keypoint localization models is limited by keypoint priors provided by the training data. To alleviate this restriction and pursue more general model this work studies keypoint localization from a different perspective by reasoning locations based on keypiont clues in…
Recently, unified speech-text models, such as SpeechGPT, VioLA, and AudioPaLM, have achieved remarkable performance on various speech tasks. These models discretize speech signals into tokens (speech discretization) and use a shared vocabulary for both text and speech tokens. Then they train a singl…
The challenge of open-vocabulary recognition lies in the model has no clue of new categories it is applied to. Existing works have proposed different methods to embed category cues into the model e.g. through few-shot fine-tuning providing category names or textual descriptions to Vision-Language Mo…
Multi-modal Large Language Models (MLLMs) have shown remarkable capabilities in various multi-modal tasks. Nevertheless their performance in fine-grained image understanding tasks is still limited. To address this issue this paper proposes a new framework to enhance the fine-grained image understand…
Bio-inspired spike camera mimics the sampling principle of primate fovea. It presents high temporal resolution and dynamic range, showing great promise in fast-moving object recognition. However, the physical limit of CMOS technology in spike cameras still hinders their capability of recognizing ult…
Hotword customization is one of the concerned issues remained in ASR field - it is of value to enable users of ASR systems to customize names of entities, persons and other phrases to obtain better experience. The past few years have seen effective modeling strategies for ASR contextualization devel…
Multi-Modal automatic speech recognition (ASR) techniques aim to leverage additional modalities to improve the performance of speech recognition systems. While existing approaches primarily focus on video or contextual information, the utilization of extra supplementary textual information has been…
Regression-based keypoint localization shows advantages of high efficiency and better robustness to quantization errors than heatmap-based methods. However existing regression-based methods discard the spatial location prior in input image with a global pooling leading to inferior accuracy and are l…
We propose emotion2vec, a universal speech emotion representation model. emotion2vec is pre-trained on open-source unlabeled emotion data through self-supervised online distillation, combining utterance-level loss and frame-level loss during pre-training. emotion2vec outperforms state-of-the-art pre…
Model-based 3D human mesh recovery aims to reconstruct a 3D human body mesh by estimating its parameters from monocular RGB images. Most of recent works adopt the Skinned Multi-Person Linear (SMPL) model to regress relative rotations for each body joint along the kinematics chain. This pipeline need…
Existing Masked Image Modeling methods apply fixed mask patterns to guide the self-supervised training. As those patterns resort to different criteria to mask local regions, sticking to a fixed pattern leads to limited vision cues modeling capability. This paper proposes an evolved part-based maskin…
Transformers have shown great potential in various computer vision tasks. By borrowing design concepts from transformers, many studies revolutionized CNNs and showed remarkable results. This paper falls in this line of studies. Specifically, we propose a new convolutional neural network, ParCNetV2,…
In recent years, the joint training of speech enhancement front-end and automatic speech recognition (ASR) back-end has been widely used to improve the robustness of ASR systems. Traditional joint training methods only use enhanced speech as input for the backend. However, it is difficult for speech…
Recently, end-to-end neural diarization (EEND) is introduced and achieves promising results in speaker-overlapped scenarios. In EEND, speaker diarization is formulated as a multi-label prediction problem, where speaker activities are estimated independently and their dependency are not well consider…
Due to its promising performance, deep hashing has become a prevalent method for approximate nearest neighbors search (ANNs). However, most of current deep hashing methods are validated on relatively small-scale datasets, leaving potential threats when are applied to large-scale real-world scenarios…
Crowded scenes make it challenging to differentiate persons and locate their pose keypoints. This paper proposes the Contextual Instance Decoupling (CID), which presents a new pipeline for multi-person pose estimation. Instead of relying on person bounding boxes to spatially differentiate persons, C…
Recent development of speech signal processing, such as speech recognition, speaker diarization, etc., has inspired numerous applications of speech technologies. The meeting scenario is one of the most valuable and, at the same time, most challenging scenarios for the deployment of speech technologi…
Keyphrase extraction (KPE) automatically extracts phrases in a document that provide a concise summary of the core content, which benefits downstream information retrieval and NLP tasks. Previous state-of-the-art methods select candidate keyphrases based on the similarity between learned representat…
The novel working principle enables spiking cameras to capture high-speed moving objects. However, the applications of spiking cameras can be affected by many factors, such as brightness intensity, detectable distance, and the maximum speed of moving targets. Improper settings such as weak ambient b…
Expressive text-to-speech (TTS) has become a hot research topic recently, mainly focusing on modeling prosody in speech. Prosody modeling has several challenges: 1) the extracted pitch used in previous prosody modeling works have inevitable errors, which hurts the prosody modeling; 2) different attr…
Recently, hybrid systems of clustering and neural diarization models have been successfully applied in multi-party meeting analysis. However, current models always treat overlapped speaker diarization as a multi-label classification problem, where speaker dependency and overlaps are not well conside…
The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Grand Challenge (M2MeT) focuses on one of the most valuable and the most challenging scenarios of speech technologies. The M2MeT challenge has particularly set up two tracks, speaker diarization (track 1) and multi-speaker automatic spe…
Event cameras encode the change of brightness into events, differing from conventional frame cameras. The novel working principle makes them to have stronger potential in high-speed applications. However, the lack of labeled event annotations limits the applications of such cameras in deep learning…
Recent works show that mean-teaching is an effective framework for unsupervised domain adaptive person re-identification. However, existing methods perform contrastive learning on selected samples between teacher and student networks, which is sensitive to noises in pseudo labels and neglects the re…
Most of unsupervised person Re-Identification (Re-ID) works produce pseudo-labels by measuring the feature similarity without considering the distribution discrepancy among cameras, leading to degraded accuracy in label computation across cameras. This paper targets to address this challenge by stud…
Multi-person pose estimation in crowded scenes is challenging because overlapping and occlusions make it difficult to detect person bounding boxes and infer pose cues from individual keypoints. To address those issues, this paper proposes a direct pose-level inference strategy that is free of boundi…
Unsupervised domain adaptive person Re-IDentification (ReID) is challenging because of the large domain gap between source and target domains, as well as the lackage of labeled data on the target domain. This paper tackles this challenge through jointly enforcing visual and temporal consistency in t…
Current methods for monaural speech enhancement only utilize acoustic information but seldom consider the phonetic information of an utterance. In the voice conversion community, significant progress has been achieved by using the phonetic information via the phonetic posteriorgrams (PPGs). Inspired…
Various factors like occlusions, backgrounds, etc., would lead to misaligned detected bounding boxes , e.g., ones covering only portions of human body. This issue is common but overlooked by previous person search works. To alleviate this issue, this paper proposes an Align-to-Part Network (APNet) f…
The challenge of unsupervised person re-identification (ReID) lies in learning discriminative features without true labels. This paper formulates unsupervised person ReID as a multi-label classification task to progressively seek true labels. Our method starts by assigning each person image with a s…
Exploiting multi-scale representations is critical to improve edge detection for objects at different scales. To extract edges at dramatically different scales, we propose a Bi-Directional Cascade Network (BDCN) structure, where an individual layer is supervised by labeled edges at its specific scal…
This paper proposes the Global-Local Temporal Representation (GLTR) to exploit the multi-scale temporal cues in video sequences for video person Re-Identification (ReID). GLTR is constructed by first modeling the short-term temporal cues among adjacent frames, then capturing the long-term relations…
The choice of acoustic modeling units is critical to acoustic modeling in large vocabulary continuous speech recognition (LVCSR) tasks. The recent connectionist temporal classification (CTC) based acoustic models have more options for the choice of modeling units. In this work, we propose a DFSMN-CT…
Audio-visual speech recognition (AVSR) is thought to be one of the potential solutions for robust speech recognition, especially in noisy environments. Compared to audio only speech recognition, the major issues of AVSR include the lack of publicly available audio-visual corpora and the need of robu…
The Bidirectional LSTM (BLSTM) RNN based speech synthesis system is among the best parametric Text-to-Speech (TTS) systems in terms of the naturalness of generated speech, especially the naturalness in prosody. However, the model complexity and inference cost of BLSTM prevents its usage in many runt…
In this paper, we present an improved feedforward sequential memory networks (FSMN) architecture, namely Deep-FSMN (DFSMN), by introducing skip connections between memory blocks in adjacent layers. These skip connections enable the information flow across different layers and thus alleviate the grad…
Although the performance of person Re-Identification (ReID) has been significantly boosted, many challenging issues in real scenarios have not been fully investigated, e.g., the complex scenes and lighting variations, viewpoint and pose changes, and the large number of identities in a camera network…
Feature extraction and matching are two crucial components in person Re-Identification (ReID). The large pose deformations and the complex view variations exhibited by the captured person images significantly increase the difficulty of learning and matching of the features from person images. To ove…
We propose a novel Multi-Task Learning with Low Rank Attribute Embedding (MTL-LORAE) framework for person re-identification. Re-identifications from multiple cameras are regarded as related tasks to exploit shared information to improve re-identification accuracy. Both low level features and semanti…