50 accepted papers
Vision–Language–Action (VLA) models in autonomous driving systems have recently demonstrated transformative potential by integrating multimodal perception with decision-making capabilities. However, the interpretability and coherence of the decision process and the plausibility of action sequences r…
As super-resolution (SR) techniques advance, we observe a growing distrust of evaluation metrics in recent SR research. An inconsistency often emerges between certain evaluation criteria and human perceptual preference. Although current SR research employs varying metrics to evaluate SR performance,
Diffusion Probabilistic Models have demonstrated remarkable performance across a wide range of generative tasks. However, we have observed that these models often suffer from a Signal-to-Noise Ratio-timestep (SNR-t) bias. This bias refers to the misalignment between the SNR of the denoising sample a
Pre-trained text-to-image (T2I) generative priors have shown success in depth and normal prediction. However, dense prediction is inherently an image-to-image task, suggesting that image editing models, rather than T2I generative models, may be a more suitable foundation for fine-tuning. Motivated b
Image Chain-of-Thought (Image-CoT) is a test-time scaling paradigm that improves image generation by extending inference time. Most Image-CoT methods focus on text-to-image (T2I) generation. Unlike T2I generation, image editing is goal-directed: the solution space is constrained by the source image
Tightly coupled LiDAR–inertial odometry (LIO) systems are critical for autonomous navigation, yet their performance often degrades due to insufficient adaptability to diverse environments and limitations in map representation. To address these limitations, this paper presents GMM-LIO, a robust and a…
Region-instructed layout control in text-to-image generation is highly practical, yet existing methods suffer from limitations: (i) training-based approaches inherit data bias and often degrade image quality, and (ii) current techniques struggle with occlusion order, limiting real-world usability. T
Beyond the commonly recognized optical aberrations, the imaging performance of simplified optical systems--including single-lens and metalens designs--is often further degraded by veiling glare caused by stray-light scattering from non-ideal optical surfaces and coatings, particularly in complex rea
Feature matching is a fundamental technique in visual perception, essential for tasks such as 3D reconstruction, SLAM, and visual localization. Existing detector-free methods often struggle with generalization due to their reliance on depth data, which is not available in many datasets. We propose P…
Robust all-weather localization is a critical capability for autonomous systems. While 4D mmWave radar offers superior resilience to adverse environmental conditions compared to LiDAR and cameras, its application in high-precision Simultaneous Localization and Mapping (SLAM) is hindered by significa…
Generating human videos with realistic and controllable motions is a challenging task. While existing methods can generate visually compelling videos, they lack separate control over four key video elements: foreground subject, background video, human trajectory, and action patterns. In this paper, …
Controllable image synthesis, which enables fine-grained control over generated outputs, has emerged as a key focus in visual generative modeling. However, controllable generation remains challenging for Visual Autoregressive (VAR) models due to their hierarchical, next-scale prediction style. Exist
Recently, autoregressive (AR) models have shown strong potential in image generation, offering better scalability and easier integration with unified multi-modal models compared to diffusion methods.However, extending AR models to controllable image editing remains challenging due to weak and ineffi
Prevalent Computational Aberration Correction (CAC) methods are typically tailored to specific optical systems, leading to poor generalization and labor-intensive re-training for new lenses.Developing CAC paradigms capable of generalizing across diverse photographic lenses offers a promising solutio
Despite advances in the application of MLLMs for various video tasks, video event prediction (VEP) remains relatively underexplored. VEP requires the model to perform fine-grained temporal modeling of videos and establish logical relationships between videos and future events, which current MLLMs st
Multimodal large language models (MLLMs) have demonstrated remarkable potential in bridging visual and textual reasoning, yet their reliance on text-centric priors often limits their ability to disentangle semantically similar actions in open-vocabulary scenarios. To address this, we propose Video-S…
This paper introduces Swap Forward (SaFa), a modality-agnostic and efficient method to generate seamless and coherent long spectrum and panorama using a latent swap joint diffusion process across multi-views. We first investigate spectrum aliasing problem in spectrum-based audio generation caused by…
Detection of deformable linear objects (DLOs) in three-dimensional space is essential for robotic manipulation of DLOs. However, their complex deformations and high degrees of freedom make perception highly susceptible to occlusions, noise, and data missing. To address these challenges, we propose a
Low-light image enhancement (LLIE) aims to improve the visibility of images captured in poorly lit environments. Prevalent event-based solutions primarily utilize events triggered by motion, i.e., "motion events" to strengthen only the edge texture, while leaving the high dynamic range and excellent…
4D mmWave radar provides the point cloud with range, azimuth, elevation, Doppler velocity and operates normally in severe weather conditions. However, due to wavelength characteristics, the noisy and sparse point cloud that 4D radar collects poses great challenges for SLAM research. In this paper, w
Deep learning (DL)-based speaker diarization methods have proven powerful performance comparing to traditional clustering-based methods for multi-talker speech diarization and recognition in farfield scenes. However, most DL-based approaches cannot utilize the spatial information well due to the poo…
Robot-assisted Natural Orifice Translu-minal Endoscopic Surgery (NOTES) represents a paradigm shift in surgical practice, significantly mini-mizing patient morbidity. However, the variability of inner diameter and the inter-luminal crossing within the luminal tracts lead to challenge for effective r…
In multi-speaker scenarios, automatic speech recognition (ASR) models rely on pre-processed audio after speaker separation. However, when the target speaker is not accurately separated, ASR models face limitations in reaching their peak performance. To address this issue, we propose a speaker-adapti…
Foundation models have demonstrated significant emergent abilities, holding great promise for enhancing embodied agents' reasoning and planning capacities. However, the absence of a comprehensive benchmark for evaluating embodied agents with multimodal observations in complex environments remains a…
The integration of Large Language Models (LLMs) and knowledge graphs (KGs) has achieved remarkable success in various natural language processing tasks. However, existing methodologies that integrate LLMs and KGs often navigate the task-solving process solely based on the LLM’s analysis of the quest…
Geometric perception problems are fundamental tasks in robotics and computer vision. In real-world applications, they often encounter the inevitable issue of outliers, preventing traditional algorithms from making correct estimates. In this paper, we present a novel general-purpose robust estimator…
Personality recognition aims to identify the personality traits implied in user data such as dialogues and social media posts. Current research predominantly treats personality recognition as a classification task, failing to reveal the supporting evidence for the recognized personality. In this pap…
In this paper, we present a new question-answering (QA) based key-value pair extraction approach, called KVPFormer, to robustly extracting key-value relationships between entities from form-like document images. Specifically, KVPFormer first identifies key entities from all entities in an image with…
We study four data augmentation (DA) techniques and two model architectures on realistic data for sound event localization and detection (SELD). First, based on ResNet-Conformer (RC), we compare the four DA approaches on the realistic DCASE 2022 SELD test set which is often not easy to handle due to…
One-to-one set matching is a key design for DETR to establish its end-to-end capability, so that object detection does not require a hand-crafted NMS (non-maximum suppression) to remove duplicate detections. This end-to-end signature is important for the versatility of DETR, and it has been generali…
The performance of video frame interpolation is inherently correlated with the ability to handle motion in the input scene. Even though previous works recognize the utility of asynchronous event information for this task, they ignore the fact that motion may or may not result in blur in the input vi…
Transducer is one of the mainstream frameworks for streaming speech recognition. There is a performance gap between the streaming and non-streaming transducer models due to limited context. To reduce this gap, an effective way is to ensure that their hidden and output distributions are consistent, w…
"Traditional frame-based cameras inevitably suffer from motion blur due to long exposure times. As a kind of bio-inspired camera, the event camera records the intensity changes in an asynchronous way with high temporal resolution, providing valid image degradation information within the exposure tim…
In this paper, we propose an iterative separation-based speaker diarization (ISSD) approach to cope with the realistic data conditions. In the proposed ISSD, we iteratively generate adaptation data ac-cording to speaker priors and fine-tune the separation model, which leads to a gradual performance…
Vision Transformer (ViT) attains state-of-the-art performance in visual recognition, and the variant, Local Vision Transformer, makes further improvements. The major component in Local Vision Transformer, local attention, performs the attention separately over small local windows. We rephrase local…
Correspondence-based rotation search and point cloud registration are two fundamental problems in robotics and computer vision. However, the presence of outliers, sometimes even occupying the great majority of the putative correspondences, can make many existing algorithms either fail or have very h
Correspondence-based point cloud registration is a cornerstone in robotics perception and computer vision, which seeks to estimate the best rigid transformation aligning two point clouds from the putative correspondences. However, due to the limited robustness of 3D keypoint matching approaches, out
The recently-developed DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the critical issue, slow training convergence, and present a conditional cross-attention mechanism for fast DETR training. Ou…
In this paper, we design a novel joint framework of speech enhancement and speech separation for child speech extraction in realistic conditions, targeting the problem of extracting child speech from daily conversations in BabyTrain mega corpus. To the best of our knowledge, it is the first discussi…
One-class novelty detection is to identify anomalous instances that do not conform to the expected normal instances. In this paper, the Generative Adversarial Networks (GANs) based on encoder-decoder-encoder pipeline are used for detection and achieve state-of-the-art performance. However, deep neur…
In this paper, we design a novel front-end processing system for speaker diarization under realistic conditions with challenging background noises. To cope with diversified environments, we first extend our perviously proposed progressive learning based speech enhancement model by adding multi-task…
Semantic segmentation has made striking progress due to the success of deep convolutional neural networks. Considering the demands of autonomous driving, real-time semantic segmentation has become a research hotspot these years. However, few real-time RGB-D fusion semantic segmentation studies are c
In this paper, we design a two-stage single-channel speaker-dependent speech separation approach for the CHiME-5 Challenge, targeting the problem of far-field and multi-talker conversational speech recognition in dinner party scenarios involving background noises, reverberations and overlapping spee…
The conventional speaker recognition frameworks (e.g., the i-vector and CNN-based approach) have been successfully applied to various tasks when the channel of the enrolment dataset is similar to that of the test dataset. However, in real-world applications, mismatch always exists between these two…
In this study, we investigate on the effects of deep learning based speech enhancement as a preprocessor to speaker diarization in quite challenging realistic environments involving the background noises, reverberations and overlapping speech. To improve the generalization capability, the advanced l…
Automatic speech recognition is more and more widely and effectively used. Nevertheless, in some automatic speech analysis tasks the state of the art is surprisingly poor. One of these is “diarization”, the task of determining who spoke when. Diarization is key to processing meeting audio and clinic…
Orientation control is an important topic with many applications including robotic manipulation, spacecraft control, etc. The orientation control is particularly challenging when the system model is unknown due to the fact that the rotation group is a nonlinear manifold. In this letter, we propose a
In this paper, we investigate the convergence performance of a sparsified kernel least mean square (KLMS) algorithm in which the input is added into the dictionary only when the prediction error in amplitude is larger than a preset threshold. Under certain conditions, we derive an approximate value…
Independent component analysis (ICA) by an information measure has seen wide applications in engineering. Different from traditional probability density function based information measures, a probability survival distribution based Cauchy-Schwartz information measure for multiple variables is propos…
This paper presents a practical control approach for series elastic actuators(SEAs) to generate the desired torque. Specifically, the controller is applicable to both linear and nonlinear SEAs and it works well even in the presence of unknown payload parameters and external disturbances. Via the ana…