29 accepted papers
Recent Vision-Language-Action (VLA) models map visual-textual inputs to robotic actions via end-to-end architectures, yet this approach entangles visual understanding with task-specific actions. This leads to an exhaustive collection of full operational sequences and parameter redundancy across task
Audio-visual deepfake detection typically employs a complementary multi-modal model to check the forgery traces in the video. These methods primarily extract forgery traces through audio-visual alignment, which results from the inconsistency between audio and video modalities. However, the tradition…
Federated learning (FL) enables collaborative training across distributed edge devices, but deploying lightweight models in dynamic edge environments remains challenging. Existing methods typically require retraining whenever device resource constraints change, resulting in excessive computational o…
The latest advancements in scene relighting have been predominantly driven by inverse rendering with 3D Gaussian Splatting (3DGS). However, existing methods remain overly reliant on precise camera parameters under static illumination conditions, which is prohibitively expensive and even impractical
Recent advances in 3D Gaussian Splatting (3DGS) enable photorealistic real-time rendering but also increase the risks of unauthorized copying and redistribution. Existing 3DGS watermarking methods typically rely on handcrafted thresholds or globally fixed hyperparameters to balance invisibility and
Gaussian splatting techniques have recently revolutionized outdoor scene decomposition and relighting through multi-view images. However, achieving high rendering quality still requires a fixed lighting condition among all input views, which is costly or even impractical to capture in outdoor scenes
The 3D perception of satellites, including both their shape and pose, is a key foundation for robotic on-orbit servicing. However, the demanding space environment-such as intense and dim illumination-presents significant challenges. Previous non-cooperative methods focus on specific geometric featur
Rencent advancements in large language models (LLM) have shown impressive versatility across various tasks. Short text matching is one of the fundamental technologies in natural language processing. In previous studies, the common approach to applying them to Chinese is segmenting each sentence into
Network quantization effectively reduces both memory footprints and inference time of deep neural networks, enabling their deployment on resource-constrained devices. To fully utilize the multiple bit-width arithmetic operations of the hardware, mixed-precision quantization (MPQ) is developed to ass…
This paper proposes a method to estimate the wheel slip ratio and side slip angle of wheeled rovers by processing images of wheel trace imprints. The proposed method extracts structural features from trace imprint images, such as the trace unit, trace contour, and angle between the centerline of the
The latest advancements in scene relighting have been predominantly driven by inverse rendering with 3D Gaussian Splatting (3DGS). However, existing methods remain overly reliant on densely sampled images under static illumination conditions, which is prohibitively expensive and even impractical in…
In neural architecture search (NAS), the relativistic predictor has recently emerged as an attractive technique to solve ranking issue for performance evaluation by predicting the relativistic ranking of architecture pair rather than the absolute performance of an architecture. However, it suffers f
Speech bandwidth extension (BWE) has demonstrated promising performance in enhancing the perceptual speech quality in real communication systems. Most existing BWE researches primarily focus on fixed upsampling ratios, disregarding the fact that the effective bandwidth of captured audio may fluctuat…
Category-level object pose estimation demonstrates robust generalization capabilities that benefit robotics applications. However, exclusive reliance on RGB images without leveraging any 3D information introduces ambiguity in the translation and size of objects, leading to suboptimal performance. In…
Speech applications are expected to be low-power and robust under noisy conditions. An effective Voice Activity Detection (VAD) front-end lowers the computational need. Spiking Neural Networks (SNNs) are known to be biologically plausible and power-efficient. However, SNN-based VADs have yet to achi…
In this paper, we study the intrinsic connections between informative representation among different views and sufficient information among reconstructed views in multi-view clustering. To this end, we propose a novel method called underlying-complementarity and surrounding-correspondence for multi-…
This paper describes our submission to the fourth Acoustic Echo Cancellation (AEC) Challenge, which is part of ICASSP 2023 Signal Processing Grand Challenge. The proposed system is developed based on our earlier system submitted to the ICASSP 2022 AEC challenge with significant latency and network s…
Hearing aids can improve auditory perception for hearing-impaired (HI) listeners, but even state-of-art devices provide only limited benefits if not configured correctly for the listeners. The prescriptive fittings of hearing aids ignore the individual difference among HI listeners with identical he…
Recently, word enhancement has become very popular for Chinese Named Entity Recognition (NER), reducing segmentation errors and increasing the semantic and boundary information of Chinese words. However, these methods tend to ignore the semantic relationship before and after the sentence after integ…
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…
Deep learning based wideband (16kHz) acoustic echo cancellation (AEC) approaches have surpassed traditional methods. This work proposes a deep hierarchical fusion (DHF) network with intra-network and inter-network fusion to further improve the wideband AEC performance. Meanwhile, this work extends t…
Goal inference is of great importance for a variety of applications that involve interaction, coordination, and/or competition with goal-oriented agents. Typical goal inference approaches use as many pointwise measurements of the agent's trajectory as possible to pursue a most accurate a-posteriori…
Aiming to find a program satisfying the user intent given input-output examples, program synthesis has attracted increasing interest in the area of machine learning. Despite the promising performance of existing methods, most of their success comes from the privileged information of well-designed in…
With the development of Chinese medical insurance industry, the amount of claim cases is growing rapidly. Ultimately, more claims necessarily indicate that the insurance company has to spend much time assessing claims and decides how much compensation the claimant should receive, which is a highly p…
Voice activity detection (VAD) based on deep learning has achieved remarkable success. However, when the traditional features (e.g., raw waveforms and MFCCs) are directly fed to the deep neural network model, the performance decreases because of noise interference. Here, we propose a robust VAD appr…
Deep networks excel in learning patterns from large amounts of data. On the other hand, many geometric vision tasks are specified as optimization problems. To seamlessly combine deep learning and geometric vision, it is vital to perform learning and geometric optimization end-to-end. Towards this ai…
Non-Maximum Suppression (NMS) is an essential step of modern object detection models for removing duplicated candidates. The efficacy of NMS heavily affects the final detection results. Prior works exploit suppression criterions relying on either the objectiveness derived from classification or the…
In an autonomous scientific exploration system, the terrain map generated from mapping process integrates sensing information from multiple aspects and lays the base for decision making processes. With the increasing challenges in planetary exploration, equipping planetary rovers with the principles…