37 accepted papers
Cross-modal 2D–3D gait recognition is impeded by inherent domain discrepancies between 2D silhouette and 3D point cloud distributions. While prior methods align only final embeddings, we propose DiffCrossGait, which enforces trajectory-level alignment by driving both modalities with shared noise in …
Large-scale self-supervised Pre-Trained Models (PTMs) have shown significant improvements in the speaker verification (SV) task by providing rich feature representations. In this paper, we utilize w2v-BERT 2.0, a model with approximately 600 million parameters trained on 4.5 million hours of unlabel…
Machine unlearning (MUL) aims to remove the influence of specific data from a trained model for data privacy and model adaptability. Existing MUL methods mostly assume the internal parameters and the training data of the target model are accessible. Nevertheless, in most practical scenarios, the mod
3D object detection in adverse weather is crucial for autonomous driving, especially in smoke where LiDAR data becomes sparse and noisy. Due to the lack of real smoke data, this paper introduces a physics-based simulation framework to generate realistic LiDAR point clouds of smoke and augment large-
Gait recognition is a biometric technique that identifies individuals based on their walking patterns, offering advantages in long-range, non-intrusive scenarios. However, real-world scenarios often involve heterogeneous sensing modalities such as LiDAR and RGB cameras, making LiDAR-Camera Cross-mod
Gait recognition is an emerging biometric technology that enables non-intrusive and hard-to-spoof human identification. However, most existing methods are confined to short-range, unimodal settings and fail to generalize to long-range and cross-distance scenarios under real-world conditions. To addr
Rhetorical strategies are central to persuasive communication, from political discourse and marketing to legal argumentation. However, analysis of rhetorical strategies has been limited by reliance on human annotation, which is costly, inconsistent, difficult to scale. Their associated datasets are
We leverage 3D Gaussian Splatting (3DGS) as a scene representation and propose a novel test-time camera pose refinement (CPR) framework, GS-CPR. This framework enhances the localization accuracy of state-of-the-art absolute pose regression and scene coordinate regression methods. The 3DGS model rend…
Music performances, characterized by dense and continuous audio as well as seamless audio-visual integration, present unique challenges for multimodal scene understanding and reasoning. Recent Music Performance Audio-Visual Question Answering (Music AVQA) datasets have been proposed to reflect these…
This paper proposes a general solution to enable point cloud recognition models to handle distribution shifts at test time. Unlike prior methods, which rely heavily on training data (often inaccessible during online inference) and are limited to recognizing a fixed set of point cloud classes predefi…
Visual Question Answering (VQA) is increasingly used in diverse applications ranging from general visual reasoning to safety-critical domains such as medical imaging and autonomous systems, where models must provide not only accurate answers but also explanations that humans can easily understand an
Emergency traffic control presents an increasingly critical challenge, requiring seamless coordination among emergency vehicles, regular vehicles, and traffic lights to ensure efficient passage for all vehicles. Existing models primarily only focus on traffic light control, leaving emergency and reg…
Lay paraphrasing aims to make scientific information accessible to audiences without technical backgrounds. However, most existing studies focus on a single domain, such as biomedicine. With the rise of interdisciplinary research, it is increasingly necessary to comprehend knowledge spanning multipl…
Multimodal foundation models (MFMs) have demonstrated significant success in tasks such as visual captioning, question answering, and image-text retrieval. However, these models face inherent limitations due to their finite internal capacity, which restricts their ability to process extended tempora…
Existing text simplification or paraphrase datasets mainly focus on sentence-level text generation in a general domain. These datasets are typically developed without using domain knowledge. In this paper, we release a novel dataset, VTechAGP, which is the first academic-to-general-audience text par…
Existing zero-shot product attribute value (aspect) extraction approaches in e-Commerce industry rely on uni-modal or multi-modal models, where the sellers are asked to provide detailed textual inputs (product descriptions) for the products. However, manually providing (typing) the product descripti…
We focus on the domain adaptation problem for 3D semantic segmentation, addressing the challenge of data variability in point clouds collected by different LiDARs. Existing benchmarks often mix different types of datasets, which blurs and complicates segmentation evaluations. Here, we introduce a Mu…
3D synthetic-to-real unsupervised domain adaptive segmentation is crucial to annotating new domains. Self-training is a competitive approach for this task but its performance is limited by different sensor sampling patterns (i.e. variations in point density) and incomplete training strategies. In th…
Soft robotic gloves can not only provide timely, effective, safe and cheap rehabilitation training for patients with impaired movement function of hand, but also assist in completing daily grasping activities. However, most soft robotic gloves are completely composed of flexible structures. Although…
Absolute pose regression (APR) estimates global pose in an end-to-end manner achieving impressive results in learn-based LiDAR localization. However compared to the top-performing methods reliant on 3D-3D correspondence matching APR's accuracy still has room for improvement. We recognize APR's lack…
Personal voice activity detection (PVAD) is gradually used in speech assistants. Traditional PVAD schemes extract the target speaker’s embedding from existing query reference speech through a pre-trained speaker verification model. Consequently, the performance of the PVAD model may suffer if the qu…
In this paper, we introduce a novel approach that unifies Automatic Speech Recognition (ASR) and speaker diarization in a cohesive framework. Utilizing the synergies between the two tasks, our method effectively extracts speaker-specific information from the lower layers of a pretrained Conformer-ba…
Music performances are representative scenarios for audio-visual modeling. Unlike common scenarios with sparse audio, music performances continuously involve dense audio signals throughout. While existing multimodal learning methods on the audio-video QA demonstrate impressive capabilities on genera…
This paper explores the optimal containment control problem for nonlinear and underactuated quadrotors with multiple team leaders governed by nonlinear dynamics, employing the reinforcement learning. A cascade controller is formulated, comprising a position control component to ensure containment ac…
In recent years, neural network-based Wake Word Spotting achieves good performance on clean audio samples but struggles in noisy environments. Audio-Visual Wake Word Spotting (AVWWS) receives lots of attention because visual lip movement information is not affected by complex acoustic scenes. Previo…
For non-sighted and visually impaired (BVI) amputees, the combined loss of vision and grasping abilities turns the seemingly simple task of reaching and grasping into a significant challenge. This letter introduces a novel multi-sensory prosthesis system designed for BVI amputees to assist in percep
In this paper, we introduce a large-scale and high-quality audiovisual speaker verification dataset, named VoxBlink. We propose an innovative and robust automatic audio-visual data mining pipeline to curate this dataset, which contains 1.45M utterances from 38K speakers. Due to the inherent nature o…
The art of communication beyond speech there are gestures. The automatic co-speech gesture generation draws much attention in computer animation. It is a challenging task due to the diversity of gestures and the difficulty of matching the rhythm and semantics of the gesture to the corresponding spee…
Target-speaker voice activity detection is currently a promising approach for speaker diarization in complex acoustic environments. This paper presents a novel Sequence-to-Sequence Target-Speaker Voice Activity Detection (Seq2Seq-TSVAD) method that can efficiently address the joint modeling of large…
This paper further explores our previous wake word spotting system ranked 2-nd in Track 1 of the MISP Challenge 2021. First, we investigate a robust unimodal approach based on 3D and 2D convolution and adopt the simple attention module (SimAM) for our system to improve performance. Second, we explor…
This paper describes the system developed by the WHU-Alibaba team for the Multimodal Information Based Speech Processing (MISP) 2022 Challenge. We extend the Sequence-to-Sequence Target-Speaker Voice Activity Detection framework to simultaneously detect multiple speakers’ voice activities from audio…
Learning the embeddings for urban regions from human mobility data can reveal the functionality of regions, and then enables the correlated but distinct tasks such as crime prediction. Human mobility data contains rich but abundant information, which yields to the comprehensive region embeddings for…
This paper describes the system developed by the DKU team for the MISP Challenge 2021. We present a two-stage approach consisting of end-to-end neural networks for the audio-visual wake word spotting task. We first process audio and video data to give them a similar structure and then train two unim…
For a multi-fingered robot hand, the individual control over single joints cannot guarantee their fine collaboration. For achieving a high-precision synchronization, a theory of synchronous control is introduced to multi-fingered robot hands. This paper introduced a new model-free and cross-coupling…
As one of the specific vision tasks, person re-identification has become a prevalent research topic in the field of multimedia and computer vision. However, existing feature extraction methods, originating from the quality of the bounding boxes which could cause the inhomogeneity and incoherence of…
We present a novel deep convolutional network pipeline, LO-Net, for real-time lidar odometry estimation. Unlike most existing lidar odometry (LO) estimations that go through individually designed feature selection, feature matching, and pose estimation pipeline, LO-Net can be trained in an end-to-en…
This paper proposes a new end-to-end trainable matching network based on receptive field, RF-Net, to compute sparse correspondence between images. Building end-to-end trainable matching framework is desirable and challenging. The very recent approach, LF-Net, successfully embeds the entire feature e…