arXiv subjects

Bo Xu

Publications and source records attributed to Bo Xu.

At least 199 records · Page 11Linked to original sources

arXiv2022

Price DOES Matter! Modeling Price and Interest Preferences in Session-based Recommendation

Session-based recommendation aims to predict items that an anonymous user would like to purchase based on her short behavior sequence. The current approaches towards session-based recommendation only focus on modeling users' interest preferences, while they all ignore a key attribute of an item, i.e., the price. Many marketing studies have shown that the price factor significantly influences users' behaviors and the purchase decisions of users are determined by both price and interest preferences simultaneously. However, it is nontrivial to incorporate price preferences for session-based recommendation. Firstly, it is hard to handle heterogeneous information from various features of items to capture users' price preferences. Secondly, it is difficult to model the complex relations between price and interest preferences in determining user choices. To address the above challenges, we propose a novel method Co-guided Heterogeneous Hypergraph Network (CoHHN) for session-based recommendation. Towards the first challenge, we devise a heterogeneous hypergraph to represent heterogeneous information and rich relations among them. A dual-channel aggregating mechanism is then designed to aggregate various information in the heterogeneous hypergraph. After that, we extract users' price preferences and interest preferences via attention layers. As to the second challenge, a co-guided learning scheme is designed to model the relations between price and interest preferences and enhance the learning of each other. Finally, we predict user actions based on item features and users' price and interest preferences. Extensive experiments on three real-world datasets demonstrate the effectiveness of the proposed CoHHN. Further analysis reveals the significance of price for session-based recommendation.

cs.IR↗

arXiv2022

Situational Perception Guided Image Matting

Most automatic matting methods try to separate the salient foreground from the background. However, the insufficient quantity and subjective bias of the current existing matting datasets make it difficult to fully explore the semantic association between object-to-object and object-to-environment in a given image. In this paper, we propose a Situational Perception Guided Image Matting (SPG-IM) method that mitigates subjective bias of matting annotations and captures sufficient situational perception information for better global saliency distilled from the visual-to-textual task. SPG-IM can better associate inter-objects and object-to-environment saliency, and compensate the subjective nature of image matting and its expensive annotation. We also introduce a textual Semantic Transformation (TST) module that can effectively transform and integrate the semantic feature stream to guide the visual representations. In addition, an Adaptive Focal Transformation (AFT) Refinement Network is proposed to adaptively switch multi-scale receptive fields and focal points to enhance both global and local details. Extensive experiments demonstrate the effectiveness of situational perception guidance from the visual-to-textual tasks on image matting, and our model outperforms the state-of-the-art methods. We also analyze the significance of different components in our model. The code will be released soon.

cs.CV↗

arXiv2022

Consecutive Decoding for Speech-to-text Translation

Speech-to-text translation (ST), which directly translates the source language speech to the target language text, has attracted intensive attention recently. However, the combination of speech recognition and machine translation in a single model poses a heavy burden on the direct cross-modal cross-lingual mapping. To reduce the learning difficulty, we propose COnSecutive Transcription and Translation (COSTT), an integral approach for speech-to-text translation. The key idea is to generate source transcript and target translation text with a single decoder. It benefits the model training so that additional large parallel text corpus can be fully exploited to enhance the speech translation training. Our method is verified on three mainstream datasets, including Augmented LibriSpeech English-French dataset, IWSLT2018 English-German dataset, and TED English-Chinese dataset. Experiments show that our proposed COSTT outperforms or on par with the previous state-of-the-art methods on the three datasets. We have released our code at \url{https://github.com/dqqcasia/st}.

cs.CL↗

arXiv2022

Improving Cross-Modal Understanding in Visual Dialog via Contrastive Learning

Visual Dialog is a challenging vision-language task since the visual dialog agent needs to answer a series of questions after reasoning over both the image content and dialog history. Though existing methods try to deal with the cross-modal understanding in visual dialog, they are still not enough in ranking candidate answers based on their understanding of visual and textual contexts. In this paper, we analyze the cross-modal understanding in visual dialog based on the vision-language pre-training model VD-BERT and propose a novel approach to improve the cross-modal understanding for visual dialog, named ICMU. ICMU enhances cross-modal understanding by distinguishing different pulled inputs (i.e. pulled images, questions or answers) based on four-way contrastive learning. In addition, ICMU exploits the single-turn visual question answering to enhance the visual dialog model's cross-modal understanding to handle a multi-turn visually-grounded conversation. Experiments show that the proposed approach improves the visual dialog model's cross-modal understanding and brings satisfactory gain to the VisDial dataset.

cs.CV↗

arXiv2022

Tunable ferroelectric topological defects on 2D topological surfaces: strain engineering skyrmion-like polar structures in 2D materials

Polar topological structures in ferroelectric thin films have recently drawn significant interest due to their fascinating physical behaviors and promising applications in high-density nonvolatile memories. However, most polar topological patterns are only observed in the perovskites superlattices. Here, we report the discovery of the tunable ferroelectric polar topological defective structures designed and achieved by strain engineering in two-dimensional PbX (X=S, Se, and Te) materials using multiscale computational simulations. First, the first-principles calculations demonstrate the strain-induced recoverable ferroelectric phase transition in such 2D materials. The unique polar topological vortex pattern is then induced by applied mechanical indentation, evidenced by molecular dynamics simulations based on a developed deep-learning potential. According to the strain phase diagram and applied complex strain loadings, the diverse polar topological structures, including antivortex structure and flux-closure structure, are predicted to be emergent through the finite-element simulations. We conclude that strain engineering is promising to tailor various designed reversible polar topologies in ultra-flexible 2D materials, which provide excellent opportunities for next-generation nanoelectronics and sensor devices.

cond-mat.mtrl-sci↗

arXiv2022

Semantic Distillation Guided Salient Object Detection

Most existing CNN-based salient object detection methods can identify local segmentation details like hair and animal fur, but often misinterpret the real saliency due to the lack of global contextual information caused by the subjectiveness of the SOD task and the locality of convolution layers. Moreover, due to the unrealistically expensive labeling costs, the current existing SOD datasets are insufficient to cover the real data distribution. The limitation and bias of the training data add additional difficulty to fully exploring the semantic association between object-to-object and object-to-environment in a given image. In this paper, we propose a semantic distillation guided SOD (SDG-SOD) method that produces accurate results by fusing semantically distilled knowledge from generated image captioning into the Vision-Transformer-based SOD framework. SDG-SOD can better uncover inter-objects and object-to-environment saliency and cover the gap between the subjective nature of SOD and its expensive labeling. Comprehensive experiments on five benchmark datasets demonstrate that the SDG-SOD outperforms the state-of-the-art approaches on four evaluation metrics, and largely improves the model performance on DUTS, ECSSD, DUT, HKU-IS, and PASCAL-S datasets.

cs.CV↗

arXiv2022

Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection

Nowadays, most methods in end-to-end contextual speech recognition bias the recognition process towards contextual knowledge. Since all-neural contextual biasing methods rely on phrase-level contextual modeling and attention-based relevance modeling, they may encounter confusion between similar context-specific phrases, which hurts predictions at the token level. In this work, we focus on mitigating confusion problems with fine-grained contextual knowledge selection (FineCoS). In FineCoS, we introduce fine-grained knowledge to reduce the uncertainty of token predictions. Specifically, we first apply phrase selection to narrow the range of phrase candidates, and then conduct token attention on the tokens in the selected phrase candidates. Moreover, we re-normalize the attention weights of most relevant phrases in inference to obtain more focused phrase-level contextual representations, and inject position information to better discriminate phrases or tokens. On LibriSpeech and an in-house 160,000-hour dataset, we explore the proposed methods based on a controllable all-neural biasing method, collaborative decoding (ColDec). The proposed methods provide at most 6.1% relative word error rate reduction on LibriSpeech and 16.4% relative character error rate reduction on the in-house dataset over ColDec.

cs.CL↗

arXiv2022

Novel boron nitride polymorphs with graphite-diamond hybrid structure

Both boron nitride (BN) and carbon (C) have sp, sp2 and sp3 hybridization modes, and thus resulting in a variety of BN and C polymorphs with similar structures, such as hexagonal BN (hBN) and graphite, cubic BN (cBN) and diamond. Here, five types of BN polymorph structures were proposed theoretically, inspired by the graphite-diamond hybrid structures discovered in recent experiment. These BN polymorphs with graphite-diamond hybrid structures possessed excellent mechanical properties with combined high hardness and high ductility, and also exhibited various electronic properties such as semi-conductivity, semi-metallicity, and even one- and two-dimensional conductivity, differing from known insulators hBN and cBN. The simulated diffraction patterns of these BN hybrid structures could account for the unsolved diffraction patterns of intermediate products composed of "compressed hBN" and diamond-like BN, caused by phase transitions in previous experiments. Thus, this work provides a theoretical basis for the presence of these types of hybrid materials during phase transitions between graphite-like and diamond-like BN polymorphs.

cond-mat.mtrl-sci↗

arXiv2022

FAEP: Fast Autonomous Exploration Planner for UAV Equipped with Limited FOV Sensor

Autonomous exploration is one of the important parts to achieve the autonomous operation of Unmanned Aerial Vehicles (UAVs). To improve the efficiency of the exploration process, a fast and autonomous exploration planner (FAEP) is proposed in this paper. We firstly design a novel frontiers exploration sequence generation method to obtain a more reasonable exploration path, which considers not only the flight-level but frontier-level factors into TSP. According to the exploration sequence and the distribution of frontiers, a two-stage heading planning strategy is proposed to cover more frontiers by heading change during an exploration journey. To improve the stability of path searching, a guided kinodynamic path searching based on a guiding path is devised. In addition, a dynamic start point selection method for replanning is also adopted to increase the fluency of flight. We present sufficient benchmark and real-world experiments. Experimental results show the superiority of the proposed exploration planner compared with typical and state-of-the-art methods.

cs.RO↗

arXiv2022

Learning Multi-agent Action Coordination via Electing First-move Agent

Learning to coordinate actions among agents is essential in complicated multi-agent systems. Prior works are constrained mainly by the assumption that all agents act simultaneously, and asynchronous action coordination between agents is rarely considered. This paper introduces a bi-level multi-agent decision hierarchy for coordinated behavior planning. We propose a novel election mechanism in which we adopt a graph convolutional network to model the interaction among agents and elect a first-move agent for asynchronous guidance. We also propose a dynamically weighted mixing network to effectively reduce the misestimation of the value function during training. This work is the first to explicitly model the asynchronous multi-agent action coordination, and this explicitness enables to choose the optimal first-move agent. The results on Cooperative Navigation and Google Football demonstrate that the proposed algorithm can achieve superior performance in cooperative environments. Our code is available at \url{https://github.com/Amanda-1997/EFA-DWM}.

cs.MA↗

arXiv2022

Motif-topology and Reward-learning improved Spiking Neural Network for Efficient Multi-sensory Integration

Network architectures and learning principles are key in forming complex functions in artificial neural networks (ANNs) and spiking neural networks (SNNs). SNNs are considered the new-generation artificial networks by incorporating more biological features than ANNs, including dynamic spiking neurons, functionally specified architectures, and efficient learning paradigms. In this paper, we propose a Motif-topology and Reward-learning improved SNN (MR-SNN) for efficient multi-sensory integration. MR-SNN contains 13 types of 3-node Motif topologies which are first extracted from independent single-sensory learning paradigms and then integrated for multi-sensory classification. The experimental results showed higher accuracy and stronger robustness of the proposed MR-SNN than other conventional SNNs without using Motifs. Furthermore, the proposed reward learning paradigm was biologically plausible and can better explain the cognitive McGurk effect caused by incongruent visual and auditory sensory signals.

cs.NE↗

arXiv2022

GCS: Graph-based Coordination Strategy for Multi-Agent Reinforcement Learning

Many real-world scenarios involve a team of agents that have to coordinate their policies to achieve a shared goal. Previous studies mainly focus on decentralized control to maximize a common reward and barely consider the coordination among control policies, which is critical in dynamic and complicated environments. In this work, we propose factorizing the joint team policy into a graph generator and graph-based coordinated policy to enable coordinated behaviours among agents. The graph generator adopts an encoder-decoder framework that outputs directed acyclic graphs (DAGs) to capture the underlying dynamic decision structure. We also apply the DAGness-constrained and DAG depth-constrained optimization in the graph generator to balance efficiency and performance. The graph-based coordinated policy exploits the generated decision structure. The graph generator and coordinated policy are trained simultaneously to maximize the discounted return. Empirical evaluations on Collaborative Gaussian Squeeze, Cooperative Navigation, and Google Research Football demonstrate the superiority of the proposed method.

cs.MA↗

arXiv2022

Leveraging Structural Information to Improve Point Line Visual-Inertial Odometry

Leveraging line features can help to improve the localization accuracy of point-based monocular Visual-Inertial Odometry (VIO) system, as lines provide additional constraints. Moreover, in an artificial environment, some straight lines are parallel to each other. In this paper, we designed a VIO system based on points and straight lines, which divides straight lines into structural straight lines (that is, straight lines parallel to each other) and non-structural straight lines. In addition, unlike the orthogonal representation using four parameters to represent the 3D straight line, we only used two parameters to minimize the representation of the structural straight line and the non-structural straight line. Furthermore, we designed a straight line matching strategy based on sampling points to improve the efficiency and success rate of straight line matching. The effectiveness of our method is verified on both public datasets of EuRoc and TUM VI benchmark and compared with other state-of-the-art algorithms.

cs.RO↗

arXiv2022

Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problem

Deep learning based models have significantly improved the performance of speech separation with input mixtures like the cocktail party. Prominent methods (e.g., frequency-domain and time-domain speech separation) usually build regression models to predict the ground-truth speech from the mixture, using the masking-based design and the signal-level loss criterion (e.g., MSE or SI-SNR). This study demonstrates, for the first time, that the synthesis-based approach can also perform well on this problem, with great flexibility and strong potential. Specifically, we propose a novel speech separation/enhancement model based on the recognition of discrete symbols, and convert the paradigm of the speech separation/enhancement related tasks from regression to classification. By utilizing the synthesis model with the input of discrete symbols, after the prediction of discrete symbol sequence, each target speech could be re-synthesized. Evaluation results based on the WSJ0-2mix and VCTK-noisy corpora in various settings show that our proposed method can steadily synthesize the separated speech with high speech quality and without any interference, which is difficult to avoid in regression-based methods. In addition, with negligible loss of listening quality, the speaker conversion of enhanced/separated speech could be easily realized through our method.

cs.SD↗

arXiv2021

Superconductivity in graphite-diamond hybrid

Search for new high-temperature superconductors and insight into their superconducting mechanism are of fundamental importance in condensed matter physics. The discovery of near-room temperature superconductivity at more than a million atmospheres ushers in a new era for superconductors. However, the critical task of identifying materials with comparable superconductivity at near or ambient pressure remains. Carbon materials can always lead to intriguing surprises due to their structural diversity and electronic adjustability. Insulating diamond upon doping or external stimuli has achieved superconducting state. Thus, it still has a great opportunity to find superconducting ones with higher transition temperature (Tc). Here, we report an intrinsic superconducting graphite-diamond hybrid through first-principles calculations, whose atomic-resolution structural characteristics have been experimentally determined recently. The predicted Tc is approximated at 39 K at ambient pressure, and strain energizing can further boost Tc to 42 K. The strong electron-phonon coupling associated with the out-of-plane vibration of carbon atoms at the junction plays a dominant role in the superconducting transition. Our work demonstrates the great potential of such carbon materials as high-Tc superconductors, which will definitely attract extensive research.

cond-mat.mtrl-sci↗

arXiv2021

Virtual Multi-Modality Self-Supervised Foreground Matting for Human-Object Interaction

Most existing human matting algorithms tried to separate pure human-only foreground from the background. In this paper, we propose a Virtual Multi-modality Foreground Matting (VMFM) method to learn human-object interactive foreground (human and objects interacted with him or her) from a raw RGB image. The VMFM method requires no additional inputs, e.g. trimap or known background. We reformulate foreground matting as a self-supervised multi-modality problem: factor each input image into estimated depth map, segmentation mask, and interaction heatmap using three auto-encoders. In order to fully utilize the characteristics of each modality, we first train a dual encoder-to-decoder network to estimate the same alpha matte. Then we introduce a self-supervised method: Complementary Learning(CL) to predict deviation probability map and exchange reliable gradients across modalities without label. We conducted extensive experiments to analyze the effectiveness of each modality and the significance of different components in complementary learning. We demonstrate that our model outperforms the state-of-the-art methods.

cs.CV↗

arXiv2021

Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation

Several video-based 3D pose and shape estimation algorithms have been proposed to resolve the temporal inconsistency of single-image-based methods. However it still remains challenging to have stable and accurate reconstruction. In this paper, we propose a new framework Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation (DTS-VIBE), to generate 3D human pose and mesh from RGB videos. We reformulate the task as a multi-modality problem that fuses RGB and optical flow for more reliable estimation. In order to fully utilize both sensory modalities (RGB or optical flow), we train a two-stream temporal network based on transformer to predict SMPL parameters. The supplementary modality, optical flow, helps to maintain temporal consistency by leveraging motion knowledge between two consecutive frames. The proposed algorithm is extensively evaluated on the Human3.6 and 3DPW datasets. The experimental results show that it outperforms other state-of-the-art methods by a significant margin.

cs.CV↗

arXiv2021

Tao: A Learning Framework for Adaptive Nearest Neighbor Search using Static Features Only

Approximate nearest neighbor (ANN) search is a fundamental problem in areas such as data management,information retrieval and machine learning. Recently, Li et al. proposed a learned approach named AdaptNN to support adaptive ANN query processing. In the middle of query execution, AdaptNN collects a number of runtime features and predicts termination condition for each individual query, by which better end-to-end latency is attained. Despite its efficiency, using runtime features complicates the learning process and leads to performance degradation. Radically different from AdaptNN, we argue that it is promising to predict termination condition before query exetution. Particularly, we developed Tao, a general learning framework for Terminating ANN queries Adaptively using Only static features. Upon the arrival of a query, Tao first maps the query to a local intrinsic dimension (LID) number, and then predicts the termination condition using LID instead of runtime features. By decoupling prediction procedure from query execution, Tao eliminates the laborious feature selection process involved in AdaptNN. Besides, two design principles are formulated to guide the application of Tao and improve the explainability of the prediction model. We integrate two state-of-the-art indexing approaches, i.e., IMI and HNSW, into Tao, and evaluate the performance over several million to billion-scale datasets. Experimental results show that, in addition to its simplicity and generality , Tao achieves up to 2.69x speedup even compared to its counterpart, at the same high accuracy targets.

cs.DB↗