42 accepted papers
Designing heuristics for combinatorial optimization problems (COPs) is a fundamental yet challenging task that traditionally requires extensive domain expertise. Recently, Large Language Model (LLM)-based Automated Heuristic Design (AHD) has shown promise in autonomously generating heuristic compone…
Zero-shot transfer for offline reinforcement learning involves generalizing to a wide range of tasks that are often risk-sensitive, without new interaction. We show here that although Successor Features (SFs) provide a principled framework for transfer through abstracting dynamics from rewards, thei
Due to their low cost and wide field of view, monocular cameras hold great promise for visual localization. Nevertheless, significant challenges persist in associating detected semantic features with map landmarks, arising from sensing noise, depth cues, and dynamic driving scenes. Most existing app
Aerial Visual Object Search (AVOS) tasks in urban environments require Unmanned Aerial Vehicles (UAVs) to autonomously search for and identify target objects based on visual inputs without external guidance. Existing approaches struggle in complex urban environments due to redundant semantic process
Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks. However, they can be easily misled by unfaithful arguments during conversations, even when their original statements are correct. To this end, we investigate the problem of maintaining faithful integri…
Embodied Question Answering (EQA) has primarily focused on indoor environments, leaving the complexities of urban settings—spanning environment, action, and perception—largely unexplored. To bridge this gap, we introduce CityEQA, a new task where an embodied agent answers open-vocabulary questions t
Although large language models (LLMs) store vast amount of knowledge in their parameters, they still have limitations in the memorization and utilization of certain knowledge, leading to undesired behaviors such as generating untruthful and inaccurate responses. This highlights the critical need to…
Existing stereo matching techniques often struggle with detailing subtle objects on depth edges. To alleviate this problem, we introduced the Dynamic-Range Disparity Initialization module, which integrates three complementary branches: the dynamic dense volume for localized disparity sampling, the s…
The effectiveness of scaling up training data in robotic manipulation is still limited. A primary challenge in manipulation is the tasks are diverse, and the trained policy would be confused if the task targets are not specified clearly. Existing works primarily rely on text instruction to describe…
Despite the remarkable abilities of Large Language Models (LLMs) to answer questions, they often display a considerable level of overconfidence even when the question does not have a definitive answer. To avoid providing hallucinated answers to these unknown questions, existing studies typically inv…
Defocus deblurring is a classic problem in image restoration tasks. The formation of its defocus blur is related to depth. Recently, the use of dual-pixel sensor designed according to depth-disparity characteristics has brought great improvements to the defocus deblurring task. However, the difficul…
Localization based on a high-definition (HD) map is a pivotal technology for autonomous driving. Nonetheless, establishing precise data association (DA) between detected landmarks and map landmarks presents a formidable challenge when leveraging prior information on maps. Traditional DA algorithms r
In the field of binocular stereo matching, remarkable progress has been made by iterative methods like RAFT-Stereo and CREStereo. However, most of these methods lose information during the iterative process, making it difficult to generate more detailed difference maps that take full advantage of hi…
Recently, Transformer-based architectures have been explored for speaker embedding extraction. Although the Transformer employs the self-attention mechanism to efficiently model the global interaction between token embeddings, it is inadequate for capturing short-range local context, which is essent…
Recent research showed that the dual-pixel sensor has made great progress in defocus map estimation and image defocus deblurring. However, extracting real-time dual-pixel views is troublesome and complex in algorithm deployment. Moreover, the deblurred image generated by the defocus deblurring netwo…
Multi-agent reinforcement learning methods have been widely used for multi-robotic systems, and meta-learning methods are also applied to help robots reuse prior experiences to guide new tasks learning. But in some multi-robotic tasks, the robot types cannot be determined in advance or may dynamical
Existing methods of adversarial attacks successfully generate adversarial examples to confuse Deep Neural Networks (DNNs) of image classification and object detection, resulting in wrong predictions. However, these methods are difficult to attack models of video object tracking, because the tracking…
Deep reinforcement learning has been demonstrated to be an effective solution to the multi-robot collision avoidance problem. However, with existing methods, robots typically generate actions only based on local observations, sometimes augmented with global communication. Their performance deteriora
Nowadays, CNN-based stereo matching methods achieved remarkable performance, and how to efficiently exploit contextual information in cost aggregation stage is the key to improve performance. In this paper, we propose a simple yet efficient network named Hierarchical Context Guided Aggregation Netwo…
This paper describes the Microsoft speaker diarization system for monaural multi-talker recordings in the wild, evaluated at the diarization track of the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2020. We will first explain our system design to address issues in handling real multi-talker reco…
With the rapidly developing unmanned aerial vehicles, the requirements of generating maps efficiently and quickly are increasing. To realize online mapping, we develop a real-time dense mapping framework named DenseFusion which can incrementally generates dense geo-referenced 3D point cloud, digital…
Visual object tracking has made important breakthroughs with the assistance of deep learning models. Unfortunately, recent research has clearly proved that deep learning models are vulnerable to malicious adversarial attacks, which mislead the models making wrong decisions by perturbing the input im…
Deep CNN networks have shown great success in various tasks for text-independent speaker recognition. In this paper, we explore two approaches for modeling long temporal contexts to improve the performance of the ResNet networks. The first approach is simply integrating the utterance-level mean and…
Nowadays CNN-based stereo image super-resolution(SR) methods have obtained remarkable performance. However, most of existing methods only superficially portrayed the low layer features without considering the uneven distribution of information, which is insufficient because stereo image warping and…
Almost all adversarial attacks in computer vision are aimed at pre-known object categories, which could be offline trained for generating perturbations. But as for visual object tracking, the tracked target categories are normally unknown in advance. However, the tracking algorithms also have potent…
Employing attention mechanisms to model both global and local features as a final pedestrian representation has become a trend for person re-identification (Re-ID) algorithms. A potential limitation of these methods is that they focus on the most salient features, but the re-identification of a pers…
The use of deep networks to extract embeddings for speaker recognition has proven successfully. However, such embeddings are susceptible to performance degradation due to the mismatches among the training, enrollment, and test conditions. In this work, we propose an adversarial speaker verification…
The teacher-student (T/S) learning has been shown to be effective for a variety of problems such as domain adaptation and model compression. One shortcoming of the T/S learning is that a teacher model, not always perfect, sporadically produces wrong guidance in form of posterior probabilities that m…
Thanks to the development of convolutional neural networks (CNNs), researchers have proposed lots of effective semantic segmentation models. However, there are still two problems disturbing researchers, one of which is objects misidentification on the image level and another one is poor performance…
SLAM technology has recently seen many successes and attracted the attention of high-technological companies. However, how to unify the interface of existing or emerging algorithms, and effectively perform benchmark about the speed, robustness and portability are still problems. In this paper, we pr…
The chest X-ray is one of the most commonly available radiological examinations for diagnosing lung diseases. This task remains a major challenge due to 1) the shortage of accurate annotations for chest X-ray examinations, 2) the diversity of lesion areas on X-rays from different thoracic disease an…
Typical methods for supervised sequence modeling are built upon the recurrent neural networks to capture temporal dependencies. One potential limitation of these methods is that they only model explicitly information interactions between adjacent time steps in a sequence, hence the high-order intera…
This paper aims to achieve high-accuracy 3D object detection, in which we propose a novel Spatial-Channel Attention Network (SCANet), a two-stage detector that takes both LIDAR point clouds and RGB images as input to generate 3D object estimates. The first stage is a 3D region proposal network (RPN)…
This paper presents an algorithm which can generate live digtial surface model (DSM) during the flight based on simultaneous localization and mapping (SLAM). We process the keyframe which is output by a monocular SLAM system to generate a local DSM, and fuse the local DSM to the global tiled DSM inc…
This paper presents a flexible framework for the challenging task of color-guided depth upsampling. Some state-of-the-art approaches apply an aligned RGB image for depth recovery. Unfortunately, these kinds of methods may result in texture copying artifacts and edge blurring artifacts. To address th…
Voice assistant represents one of the most popular and important scenarios for speech recognition. In this paper, we propose two adaptation approaches to customize a multi-style well-trained acoustic model towards its subsidiary domain of Cortana assistant. First, we present anchor-based speaker ada…
In this paper, given the speaker bottleneck feature vectors extracted with speaker discriminant neural networks, we focus on using the sequential speaker characteristics for text-dependent speaker verification. In each evaluation trial, speaker supervectors are used as the representations of the seq…
Hard shadows detection and removal from foreground masks is a challenging step in change detection. This paper gives a simple and effective method to address hard shadows. There are inside portion and boundary portion in hard shadows. Pixel-wise neighborhood ratio is calculated to remove the most of…
Recently, the low-rank plus diagonal (LRPD) adaptation was proposed for speaker adaptation of deep neural network (DNN) models. The LRPD restructures the adaptation matrix as a superposition of a diagonal matrix and a product of two low-rank matrices. In this paper, we extend the LRPD adaptation int…
In this paper, we propose a scalable adaptation technique that adapts the deep neural network (DNN) model through the low-rank plus diagonal (LRPD) decomposition. It is desired that an adaptation method can properly accommodate the available development data with a variable amount of adaptation para…
In this paper we present a real-time approach to stitch large-scale aerial images incrementally. A monocular SLAM system is used to estimate camera position and attitude, and meanwhile 3D point cloud map is generated. When GPS information is available, the estimated trajectory is transformed to WGS8…
To develop speaker adaptation algorithms for deep neural network (DNN) that are suitable for large-scale online deployment, it is desirable that the adaptation model be represented in a compact form and learned in an unsupervised fashion. In this paper, we propose a novel low-footprint adaptation te…