119 accepted papers
Precise evidence region localization in Document Visual Question Answering (DocVQA) is crucial for improving model interpretability and reliability. However, most existing approaches rely on single-step localization, which struggles to effectively distinguish true evidence from irrelevant content wh…
Modality-agnostic Semantic Segmentation (MaSS) aims to achieve robust scene understanding across arbitrary combinations of input modality. Existing methods typically rely on explicit feature alignment to achieve modal homogenization, which dilutes the distinctive strengths of each modality and destr
Structured mesh generation serves as a crucial preprocessing step in numerical simulations and can be formulated as a mapping problem from geometry to structured mesh. Existing approaches typically establish an isolated mapping for each geometry. This geometry-specific paradigm fails to capture and
Large language models (LLMs) are widely used as reference-free evaluators via prompting, but this “LLM-as-a-Judge” paradigm is costly, opaque, and sensitive to prompt design. In this work, we investigate whether smaller models can serve as efficient evaluators by leveraging internal representations…
In deep regression, capturing the relationship among continuous labels in feature space is a fundamental challenge that has attracted increasing interest. Addressing this issue can prevent models from converging to suboptimal solutions across various regression tasks, leading to improved performance…
Dialogue agents powered by Large Language Models (LLMs) show superior performance in various tasks. Despite the better user understanding and human-like responses, their **lack of controllability** remains a key challenge, often leading to unfocused conversations or task failure. To address this, we…
Co-speech gestures are essential to non-verbal communication, enhancing both the naturalness and effectiveness of human interaction. Although recent methods have made progress in generating co-speech gesture videos, many rely on strong visual controls, such as pose images or TPS keypoint movements,…
Large language models (LLMs) often exhibit Context Faithfulness Hallucinations, where outputs deviate from retrieved information due to incomplete context integration. Our analysis reveals a strong correlation between token-level uncertainty and hallucinations. We hypothesize that attention mechanis…
Non-autoregressive (NAR) automatic speech recognition (ASR) models predict tokens independently and simultaneously, bringing high inference speed. However, there is still a gap in the accuracy of the NAR models compared to the autoregressive (AR) models. In this paper, we propose a single-step NAR A…
Recent studies have demonstrated that many layers are functionally redundant in large language models (LLMs), enabling model compression by removing these layers to reduce inference cost. While such approaches can improve efficiency, indiscriminate layer pruning often results in significant performa
Contextual biasing is essential for addressing scenario-specific challenges in End-to-End (E2E) Automatic Speech Recognition (ASR) systems. Prior contextual E2E ASR methods, such as the contextual bias with CPP Network, have utilized bias CTC loss for explicit supervision of bias tasks, However, the…
Recently, the field of Text-to-speech synthesis has been predominantly characterized by end-to-end models, with the quality of speech generated by these models becoming increasingly comparable to that of human speech. In this work, we propose a Lightweight and Efficient Text-to-speech model, a fast…
In complex electromagnetic environments, the identification and differentiation of diverse radio frequency (RF) emitters become particularly crucial. Existing RF fingerprinting methods demonstrate limitations when dealing with numerous unknown emitters, making it challenging for accurate classificat…
Enabling object detectors to recognize out-of-distribution (OOD) objects is vital for building reliable systems. A primary obstacle stems from the fact that models frequently do not receive supervisory signals from unfamiliar data, leading to overly confident predictions regarding OOD objects. Despi…
Most earlier researches on talking face generation have focused on the synchronization of lip motion and speech content. However, head pose and facial emotions are equally important characteristics of natural faces. While audio-driven talking face generation has seen notable advancements, existing m…
The rapid advancement of large language models (LLMs) has significantly enhanced their reasoning abilities, enabling increasingly complex tasks. However, these capabilities often diminish in smaller, more computationally efficient models like GPT-2. Recent research shows that reasoning distillation…
Contextual automatic speech recognition (ASR) plays an increasingly important role in addressing the long-tail issues of general ASR. In the past, contextual ASR mainly focused on phrase-level discussions, providing a convenient way to handle biasing phrases. This paper introduces a new contextual n…
Dance serves as a powerful medium for expressing human emotions but the lifelike generation of dance is still a considerable challenge. Recently diffusion models have showcased remarkable generative abilities across various domains. They hold promise for human motion generation due to their adaptabl…
Image Quality Assessment (IQA) constitutes a fundamental task within the field of computer vision yet it remains an unresolved challenge owing to the intricate distortion conditions diverse image contents and limited availability of data. Recently the community has witnessed the emergence of numerou…
"Co-speech gesture video generation is an enabling technique for many digital human applications. Substantial progress has been made in creating high-quality talking head videos. However, existing hand gesture video generation methods are primarily limited by the widely adopted 2D skeleton-based ges…
In this work, we present DFlow, a novel generative framework that combines Normalizing Flow (NF) with a Denoising AutoEncoder (DAE), for high-fidelity waveform generation. With a tactfully designed structure, DFlow seamlessly integrates the capabilities of both NF and DAE, resulting in a significant…
Existing emotional speech synthesis methods often utilize an utterance-level style embedding extracted from reference audio, neglecting the inherent multi-scale property of speech prosody. We introduce ED-TTS, a multi-scale emotional speech synthesis model that leverages Speech Emotion Diarization (…
Nowadays, singing voice conversion (SVC) has made great strides in both naturalness and similarity for common SVC with a neutral expression. However, besides singer identity, emotional expression is also essential to convey the singer’s emotions and attitudes, but current SVC systems can not effecti…
In recent years, the field of talking faces generation has attracted considerable attention, with certain methods adept at generating virtual faces that convincingly imitate human expressions. However, existing methods face challenges related to limited generalization, particularly when dealing with…
In the realm of Large Language Models (LLMs), the balance between instruction data quality and quantity is a focal point. Recognizing this, we introduce a self-guided methodology for LLMs to autonomously discern and select cherry samples from open-source datasets, effectively minimizing manual curat…
This paper addresses human-robot collaborative (HRC) precision assembly that complements natural human ability and the strength of an autonomous robot system. Our approach enables both flexibility and efficiency of tight-clearance assembly of various complex-shaped parts in the presence of uncertain…
The audio watermarking technique embeds messages into audio and accurately extracts messages from the watermarked audio. Traditional methods develop algorithms based on expert experience to embed watermarks into the time-domain or transform-domain of signals. With the development of deep neural netw…
This paper introduces INCPrompt, an innovative continual learning solution that effectively addresses catastrophic forgetting. INCPrompt’s key innovation lies in its use of adaptive key-learner and task-aware prompts that capture task-relevant information. This unique combination encapsulates genera…
In automatic speech recognition (ASR) task, the output sequence should correspond to a linear transcription of the input sequence. Lots of works have been done to learn the monotonic alignment in end-to-end (E2E) ASR model, but their methods mainly focus on streaming propose and usually result in a…
Voice conversion refers to transferring speaker identity with well-preserved content. Better disentanglement of speech representations leads to better voice conversion. Recent studies have found that phonetic information from input audio has the potential ability to well represent content. Besides,…
Large Language Models (LLMs) have shown significant promise in various applications, including zero-shot and few-shot learning. However, their performance can be hampered by inherent biases. Instead of traditionally sought methods that aim to minimize or correct these biases, this study introduces a…
This paper presents a general approach for autonomous tight-clearance assembly of complex-shaped parts using a general-purpose robot manipulator equipped with a force/torque (F/T) sensor. Such autonomous assembly is challenging in the presence of relative part pose uncertainty due to inaccuracies in
Catastrophic forgetting poses a substantial challenge for managing intelligent agents controlled by a large model, causing performance degradation when these agents face new tasks. In our work, we propose a novel solution - the Progressive Prompt Decision Transformer (P2DT). This method enhances a t…
Knowledge Graph Completion (KGC) is a task aimed at uncovering the inherent relationships among known knowledge triplets in a Knowledge Graph (KG) and subsequently predicting missing links. Presently, there is a rising interest in inductive knowledge graph completion, where missing links may pertain…
For a robot in an unknown environment to find a target semantic object, it must perform simultaneous localization and mapping (SLAM) at both geometric and semantic levels using its onboard sensors while planning and executing its motion based on the ever-updated SLAM results. In other words, the rob
Blind Omnidirectional Image Quality Assessment (BOIQA) aims to objectively assess the human perceptual quality of omnidirectional images (ODIs) without relying on pristine-quality image information. It is becoming more significant with the increasing advancement of virtual reality (VR) technology. H…
While enlightening progress has been made recently in single-target domain adaptive semantic segmentation (ST-DASS), the multi-peak distributed multi-target domain cannot be directly aligned well with the single-peak distributed source domain. As a result, it is impossible for existing methods to ha…
Out-of-distribution (OOD) detection aims at enhancing standard deep neural networks to distinguish anomalous inputs from original training data. Previous progress has introduced various approaches where the in-distribution training data and even several OOD examples are prerequisites. However, due t…
Because of predicting all the target tokens in parallel, the non-autoregressive models greatly improve the decoding efficiency of speech recognition compared with traditional autoregressive models. In this work, we present dynamic alignment Mask CTC, introducing two methods: (1) Aligned Cross Entrop…
Deep neural networks have achieved remarkable performance in retrieval-based dialogue systems, but they are shown to be ill calibrated. Though basic calibration methods like Monte Carlo Dropout and Ensemble can calibrate well, these methods are time-consuming in the training or inference stages. To…
Data-Free Knowledge Distillation (DFKD) has recently attracted growing attention in the academic community, especially with major breakthroughs in computer vision. Despite promising results, the technique has not been well applied to audio and signal processing. Due to the variable duration of audio…
Federated Learning (FL) has been widely concerned for it enables decentralized learning while ensuring data privacy. However, most existing methods unrealistically assume that the classes encountered by local clients are fixed over time. After learning new classes, this impractical assumption will m…
Detecting out-of-distribution (OOD) examples is crucial to guarantee the reliability and safety of deep neural networks in real-world settings. In this paper, we offer an innovative perspective on quantifying the disparities between in-distribution (ID) and OOD data---analyzing the uncertainty that…
Using deep learning methods to classify EEG signals can accurately identify people’s emotions. However, existing studies have rarely considered the application of the information in another domain’s representations to feature selection in the time-frequency domain. We propose a classification networ…
Music genre classification has been widely studied in past few years for its various applications in music information retrieval. Previous works tend to perform unsatisfactorily, since those methods only use audio content or jointly use audio content and lyrics content inefficiently. In addition, as…
Non-parallel many-to-many voice conversion is a kind of style transfer task in speech. Recently, AutoVC has been applied in this field as a popular solution, as it can achieve distribution-matching style transfer by training only the re- construction loss. However, in order to strike a good balance…
Deep neural retrieval models have amply demonstrated their power but estimating the reliability of their predictions remains challenging. Most dialog response retrieval models output a single score for a response on how relevant it is to a given question. However, the bad calibration of deep neural…
Not all semantics become confusing when deploying a semantic segmentation model for real-world scene understanding of adverse weather. The true semantics of most pixels have a high likelihood of appearing in the few top classes according to confidence ranking. In this paper, we replace the one-hot p…
The Retrieval Question Answering (ReQA) task employs the retrieval-augmented framework, composed of a retriever and generator. The generators formulate the answer based on the documents retrieved by the retriever. Incorporating Large Language Models (LLMs) as generators is beneficial due to their ad…
Robotic manipulation tasks rely on a plethora of environmental and payload information. One critical piece of information for accurate manipulation is the center of mass (CoM) of the object, which is essential for estimating the dynamic response of the system and determining the payload placement. T…
Recent expressive text to speech (TTS) models focus on synthesizing emotional speech, but some fine-grained styles such as intonation are neglected. In this paper, we propose QI-TTS which aims to better transfer and control intonation to further deliver the speaker’s questioning intention while tran…
This letter introduces a novel and general method to address the problem of using a general-purpose robot manipulator with a parallel gripper to wrap a deformable linear object (DLO), called a rope, around a rigid object, called a rod, autonomously. Such a robotic wrapping task has broad potential a
Voice Conversion(VC) refers to converting the voice characteristics of audio to another one as it is said by other people. Recently, more and more studies have focused on disentangle-based VC, which separates the timbre and linguistic content information from an audio signal to effectively achieve V…
In this paper, we propose a novel and general method for autonomous robotic assembly of arbitrary and complex-shaped parts in the presence of 6-dimensional uncertainty. When a nominal assembly motion of the robot holding a part is stopped by contact due to uncertainty, our method finds the best esti…
Automatic math problem solving has attracted much attention of NLP researchers recently. However, most of the works focus on the solving of Math Word Problems (MWPs). In this paper, we study on the Geometric Problem Solving based on neural networks. Solving geometric problems requires the integratio…
Voice Conversion(VC) refers to changing the timbre of a speech while retaining the discourse content. Recently, many works have focused on disentangle-based learning techniques to separate the timbre and the linguistic content information from a speech signal. Once successful, voice conversion will…
Any-to-any voice conversion problem aims to convert voices for source and target speakers, which are out of the training data. Previous works wildly utilize the disentangle-based models. The disentangle-based model assumes the speech consists of content and speaker style information and aims to unta…
Self-supervised multi-view stereopsis (MVS) attracts increasing attention for learning dense surface predictions from only a set of images without onerous ground-truth 3D training data for supervision. However, existing methods highly rely on the local photometric consistency, which fails to identif…
Deep learning methods can struggle to handle domain shifts not seen in training data, which can cause them to not generalize well to unseen domains. This has led to research attention on domain generalization (DG), which aims to the model's generalization ability to out-of-distribution. Adversarial…
Incomplete utterance rewriting (IUR) has recently become an essential task in NLP, aiming to complement the incomplete utterance with sufficient context information for comprehension. In this paper, we propose a novel method by directly extracting the coreference and omission relationship from the s…
Multimodal speech emotion recognition (SER) and sentiment analysis (SA) are important techniques for human-computer interaction. Most existing multimodal approaches utilize either shallow cross-modal fusion of pretrained features, or deep cross-modal fusion with raw features. Recently, attempts have…
Spatial-Temporal Video Super-Resolution (ST-VSR) aims to generate super-resolved videos with higher resolution (HR) and higher frame rate (HFR). Quite intuitively, pioneering two-stage based methods complete ST-VSR directly combining two sub-tasks: Spatial Video Super-Resolution (S-VSR) and Temporal…
Loop closure is necessary for correcting errors accumulated in simultaneous localization and mapping (SLAM) in unknown environments. However, conventional loop closure methods based on low-level geometric or image features may cause high ambiguity by not distinguishing similar scenarios. Thus, incor
Existing methods for speaker age estimation usually treat it as a multi-class classification or a regression problem. However, precise age identification remains a challenge due to label ambiguity, i.e., utterances from adjacent age of the same person are often indistinguishable. To address this, we…
The visual dialog task attempts to train an agent to answer multi-turn questions given an image, which requires the deep understanding of interactions between the image and dialog history. Existing researches tend to employ the modality-specific modules to model the interactions, which might be trou…
Multi-speaker text-to-speech (TTS) using a few adaption data is a challenge in practical applications. To address that, we propose a zero-shot multi-speaker TTS, named nnSpeech, that could synthesis a new speaker voice without fine-tuning and using only one adaption utterance. Compared with using a…
Grapheme-to-phoneme (G2P) conversion is the process of converting the written form of words to their pronunciations. It has an important role for text-to-speech (TTS) synthesis and automatic speech recognition (ASR) systems. In this paper, we aim to evaluate and enhance the robustness of G2P models.…
The pancreatic disease taxonomy includes ten types of masses (tumors or cysts) [20, 8]. Previous work focuses on developing segmentation or classification methods only for certain mass types. Differential diagnosis of all mass types is clinically highly desirable [20] but has not been investigated u…
Disease is one of the fundamental entities in biomedical research. Recognizing such entities from biomedical text and then normalizing them to a standardized disease vocabulary offer a tremendous opportunity for many downstream applications. Previous studies have demonstrated that joint modeling of…
In the federated learning system, parameter gradients are shared among participants and the central modulator, while the original data never leave their protected source domain. However, the gradient itself might carry enough information for precise inference of the original data. By reporting their…
This paper investigates how to correct Chinese text errors with types of mistaken, missing and redundant characters, which are common for Chinese native speakers. Most existing models based on detect-correct framework can correct mistaken characters, but cannot handle missing or redundant characters…
Accurate vertebra localization and identification are required in many clinical applications of spine disorder diagnosis and surgery planning. However, significant challenges are posed in this task by highly varying pathologies (such as vertebral compression fracture, scoliosis, and vertebral fixati…
We propose a CTC alignment-based single step non-autoregressive transformer (CASS-NAT) for speech recognition. Specifically, the CTC alignment contains the information of (a) the number of tokens for decoder input, and (b) the time span of acoustics for each token. The information are used to extrac…
Monitoring treatment response in longitudinal studies plays an important role in clinical practice. Accurately identifying lesions across serial imaging follow-up is the core to the monitoring procedure. Typically this incorporates both image and anatomical considerations. However, matching lesions…
In federated learning (FL), fair and accurate measurement of the contribution of each federated participant is of great significance. The level of contribution not only provides a rational metric for distributing financial benefits among federated participants, but also helps to discover malicious p…
In this work, we address the Text-to-Speech (TTS) task by proposing a non-autoregressive architecture called EfficientTTS. Unlike the dominant non-autoregressive TTS models, which are trained with the need of external aligners, EfficientTTS optimizes all its parameters with a stable, end-to-end trai…
Knowledge distillation refers to a technique of transferring the knowledge from a large learned model or an ensemble of learned models to a small model. This method relies on access to the original training set, which might not always be available. A possible solution is a data-free adversarial dist…
Dual-Encoders is a promising mechanism for answer retrieval in question answering (QA) systems. Currently most conventional Dual-Encoders learn the semantic representations of questions and answers merely through matching score. Researchers proposed to introduce the QA interaction features in scorin…
Existing inpainting methods have achieved promising performance in recovering defected images of specific scenes. However, filling holes involving multiple semantic categories remains challenging due to the obscure semantic boundaries and the mixture of different semantic textures. In this paper, we…
Text Normalization (TN) is an essential part in conversational systems like text-to-speech synthesis (TTS) and automatic speech recognition (ASR). It is a process of transforming non-standard words (NSW) into a representation of how the words are to be spoken. Existing approaches to TN are mainly ru…
Slot filling and intent detection have become a significant theme in the field of natural language understanding. Even though slot filling is intensively associated with intent detection, the characteristics of the information required for both tasks are different while most of those approaches may…
In this paper, we propose a novel conditional convolution network, named location-variable convolution, to model the dependencies of the waveform sequence. Different from the use of unified convolution kernels in WaveNet to capture the dependencies of arbitrary waveform, the location-variable convol…
Mammographic mass detection is an integral part of a computer-aided diagnosis system. Annotating a large number of mammograms at pixel-level in order to train a mass detection model in a fully supervised fashion is costly and time-consuming. This paper presents a novel self-training framework for se…
Although pre-trained big models (e.g., BERT, ERNIE, XLNet, GPT3 etc.) have delivered top performance in Seq2seq modeling, their deployments in real-world applications are often hindered by the excessive computations and memory demand involved. For many applications, including named entity recognitio…
Network pruning can be achieved by removing redundant channels. In this paper, we regard a channel ‘redundant’ if its output is linearly dependent with respect to those of other channels. Inspired by this, we propose an efficient pruning method, named as LDFM, by linear dependency analysis on all th…
Chinese Spelling Check (CSC) is a challenging task due to the complex characteristics of Chinese characters. Statistics reveal that most Chinese spelling errors belong to phonological or visual errors. However, previous methods rarely utilize phonological and morphological knowledge of Chinese chara…
Inspired by the contrastive predictive coding (CPC), we propose a feature representation scheme for automatic speech recognition (ASR), which encodes sequential dependency information from raw audio signals. Following the original CPC, for a given frame, mutual information (MI) lower bound is maximi…
It is often desirable to capture and map semantic information of an environment during simultaneous localization and mapping (SLAM). Such semantic information can enable a robot to better distinguish places with similar low-level geometric and visual features and perform high-level tasks that use se…
We provide a theoretical analysis on how gradient clipping affects the convergence of the incremental gradient methods on minimizing an objective function that is the sum of a large number of component functions. We show that clipping on gradients of component functions leads to bias on the descent…
Self-attention models have been successfully applied in end-to-end speech recognition systems, which greatly improve the performance of recognition accuracy. However, such attention-based models cannot be used in online speech recognition, because these models usually have to utilize a whole acousti…
Existing multi-style speech synthesis methods require either style labels or large amounts of unlabeled training data, making data acquisition difficult. In this paper, we present an unsupervised multi-style speech synthesis method that can be trained with limited data. We leverage instance discrimi…
Object detection methods are widely adopted for computer-aided diagnosis using medical images. Anomalous findings are usually treated as objects that are described by bounding boxes. Yet, many pathological findings, e.g., bone fractures, cannot be clearly defined by bounding boxes, owing to consider…
Recently, the speaker clustering model based on aggregation hierarchy cluster (AHC) is a common method to solve two main problems: no preset category number clustering and fix category number clustering. In general, model takes features like i-vectors as input of probability and linear discriminant…
Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel. AlignTTS is based on a Feed-Forward Transformer which generates mel-spectrum from a sequence of characters, and the duration of each character is determined by a duration predictor. Instea…
Trauma PXR are essential for instantaneous pelvic bone fracture detection. However, small, pathologically critical fractures can be missed, even by experienced clinicians, under the very limited diagnosis times allowed in urgent care. As a result, fracture CAD has very high demands to save time and…
Within medical imaging, organ/pathology segmentation models trained on current publicly available and fully-annotated datasets usually do not well-represent the heterogeneous modalities, phases, pathologies, and clinical scenarios encountered in real environments. On the other hand, there are tremen…
In this work, we propose Flow-TTS, a non-autoregressive end-to-end neural TTS model based on generative flow. Unlike other non-autoregressive models, Flow-TTS can achieve high-quality speech generation by using a single feed-forward network. To our knowledge, Flow-TTS is the first TTS model utilizin…
Due to the improvement of Language Modeling, the emerging NLP assistant tools aiming for text generation greatly reduce the human workload on writing documents. However, the generation of legal text faces greater challenges than ordinary texts because of its high requirement for keeping logic reason…
This paper leverages the graph-to-sequence method in neural text-to-speech (GraphTTS), which maps the graph embedding of the input sequence to spectrograms. The graphical inputs consist of node and edge representations constructed from input texts. The encoding of these graphical inputs incorporates…
Completing a corrupted image with correct structures and reasonable textures for a mixed scene remains an elusive challenge. Since the missing hole in a mixed scene of a corrupted image often contains various semantic information, conventional two-stage approaches utilizing structural information of…
Segmentation, and Registration System for 3D Multi-Modal Image Alignment of Large-scale Pathological CT Scans","Multi-modal image registration is a challenging problem that is also an important clinical task for many real applications and scenarios. As a first step in analysis, deformable registrati…
This paper introduces a feedback-based approach to interpolate video frames involving small and fast-moving objects. Unlike the existing feedforward-based methods that estimate optical flow and synthesize in-between frames sequentially, we introduce a motion-oriented component that adds a feedback b…
OAR segmentation is a critical step in radiotherapy of head and neck (H&N) cancer, where inconsistencies across radiation oncologists and prohibitive labor costs motivate automated approaches. However, leading methods using standard fully convolutional network workflows that are challenged when the…
How to reduce uncertainty in object pose estimation under complex contacts is crucial to autonomous robotic manipulation and assembly. In this paper, we introduce an approach through forecasting contact force from simulated complex contacts with calibration based on real force sensing. A constraint-…
Image landmark detection aims to automatically identify the locations of predefined fiducial points. Despite recent success in this field, higher-ordered structural modeling to capture implicit or explicit relationships among anatomical landmarks has not been adequately exploited. In this work, we p…
Deep features extracted from different domains have shown great advantages in the face anti-spoofing task. Previous extraction strategies consider less of the extent variation in distinction among feature properties. Many of them straightly make classification using the extracted information but gen…
This paper presents a novel approach to train GANs for discrete sequence generation without resorting to an explicit neural network as the discriminator. We show that when an alternative mini-max optimization procedure is performed for the value function where a closed form solution for the discrimi…
The recent proliferation of low-cost Micro Aerial Vehicles (MAV) offers an attractive means for inspecting critical infrastructure autonomously. However, to enable such autonomous tasks requires a precise spatial model of the structure and operational area, typically constructed using sensor measure…
This paper introduces a reinforcement learning algorithm with robot manipulation to learn an arbitrary object's center of mass whose physical material composition is unknown. Robot learning is through manipulation of the object in a sequence of actions. The effectiveness of the algorithm is demonstr…
Video transmission from satellites to terrestrial devices usually requires a large amount of channel resources due to the huge amount of satellite video data. Subject to limited transmission bandwidth in space environment, the video encoder for video satellite calls for higher coding efficiency. In…
The rapidly increasing surveillance video data has challenged the existing video coding standards. Even though knowledge based video coding scheme proposed for moving objects so far has achieved high efficiency, it does not take full advantages of local information and highly relies on the accuracy…
To enable autonomous robot navigation among unknown dynamic obstacles, a real-time adaptive motion planner (RAMP) plans the robot motion online based on sensing the environment as the robot moves with sensors mounted on the robot. However, the sensed environmental data from the robot's local view is…
Multi-modal data lies on heterogeneous feature spaces, which brings a significant challenge to cross-modal retrieval. Some works have been proposed to cope with this problem by learning a common subspace. However, previous methods often learn the common subspace by enhancing the relation between emb…
We present Edge-aware Context Encoder (E-CE): an image inpainting model which takes scene structure and context into account. Unlike previous CE which predicts the missing regions using context from entire image, E-CE learns to recover the texture according to edge structures, attempting to avoid co…
Continuum manipulators are particularly suitable for performing tasks in cluttered environments with limited space for maneuvering. While there is progress on continuum grasping of an object in a cluttered space, if the environment is unknown where the target object is occluded and only partially vi
It is important to enable a robot to manipulate a target object that has no 3-D model information and is situated in an environment with other unknown objects nearby. This poses an open problem of how to combine perception and manipulation to enable the robot to build an appearance-based model of th…
We introduce a novel approach to shape-based object classification and recognition through the use of a continuum manipulator. Noticing the fact that when a continuum manipulator wraps around an object in a whole-arm grasping, its own shape is indicative of the shape of the object, our approach enab…
This paper addresses the problem of real-time, non-holonomic motion planning in environments with moving obstacles of unforeseen, arbitrary motion. An approach is introduced to smoothly switch trajectories by generating feasible non-holonomic trajectory segments on the fly as the robot moves in such…
It is important to understand which view is better recognizing and reconstructing a scene for many robotic applications, especially in a cluttered environment, where objects interact and may occlude one another in all views. In this paper, we introduce a novel, learning-based approach to evaluate sc…