arXiv subjects

Li Zhang

Publications and source records attributed to Li Zhang.

At least 757 records · Page 42Linked to original sources

arXiv2020

Holistic Grid Fusion Based Stop Line Estimation

Intersection scenarios provide the most complex traffic situations in Autonomous Driving and Driving Assistance Systems. Knowing where to stop in advance in an intersection is an essential parameter in controlling the longitudinal velocity of the vehicle. Most of the existing methods in literature solely use cameras to detect stop lines, which is typically not sufficient in terms of detection range. To address this issue, we propose a method that takes advantage of fused multi-sensory data including stereo camera and lidar as input and utilizes a carefully designed convolutional neural network architecture to detect stop lines. Our experiments show that the proposed approach can improve detection range compared to camera data alone, works under heavy occlusion without observing the ground markings explicitly, is able to predict stop lines for all lanes and allows detection at a distance up to 50 meters.

cs.CV↗

arXiv2020

Near-threshold photoproduction of $J/ψ$ in two-gluon exchange model

The near-threshold photoproduction of $J/ψ$ is regarded as one golden process to unveil the nucleon mass structure, pentaquark state involving the charm quarks, and the poorly constrained gluon distribution of the nucleon at large $x$ ($>0.1$). In this paper, we present an analysis of the current experimental data under a two-gluon exchange model, which shows a good consistency. Using a parameterized function form with three free parameters, we have determined the nucleonic gluon distribution at the $J/ψ$ mass scale. Moreover, we predict the differential cross section of the electroproduction of $J/ψ$ as a function of the invariant mass of the final hadrons $W$, at EicC, as a practical application of the model and the obtained gluon distribution. According to our estimation, thousands of $J/ψ$ events can be detected per year on EicC near the threshold. Therefore, the relevant experimental measurements are suggested to be carried out on EicC.

hep-ph↗

arXiv2020

Dual Graph Convolutional Network for Semantic Segmentation

Exploiting long-range contextual information is key for pixel-wise prediction tasks such as semantic segmentation. In contrast to previous work that uses multi-scale feature fusion or dilated convolutions, we propose a novel graph-convolutional network (GCN) to address this problem. Our Dual Graph Convolutional Network (DGCNet) models the global context of the input feature by modelling two orthogonal graphs in a single framework. The first component models spatial relationships between pixels in the image, whilst the second models interdependencies along the channel dimensions of the network's feature map. This is done efficiently by projecting the feature into a new, lower-dimensional space where all pairwise interactions can be modelled, before reprojecting into the original space. Our simple method provides substantial benefits over a strong baseline and achieves state-of-the-art results on both Cityscapes (82.0% mean IoU) and Pascal Context (53.7% mean IoU) datasets. Code and models are made available to foster any further research (\url{https://github.com/lxtGH/GALD-DGCNet}).

cs.CV↗

arXiv2020

Low Complexity Trellis-Coded Quantization in Versatile Video Coding

The forthcoming Versatile Video Coding (VVC) standard adopts the trellis-coded quantization, which leverages the delicate trellis graph to map the quantization candidates within one block into the optimal path. Despite the high compression efficiency, the complex trellis search with soft decision quantization may hinder the applications due to high complexity and low throughput capacity. To reduce the complexity, in this paper, we propose a low complexity trellis-coded quantization scheme in a scientifically sound way with theoretical modeling of the rate and distortion. As such, the trellis departure point can be adaptively adjusted, and unnecessarily visited branches are accordingly pruned, leading to the shrink of total trellis stages and simplification of transition branches. Extensive experimental results on the VVC test model show that the proposed scheme is effective in reducing the encoding complexity by 11% and 5% with all intra and random access configurations, respectively, at the cost of only 0.11% and 0.05% BD-Rate increase. Meanwhile, on average 24% and 27% quantization time savings can be achieved under all intra and random access configurations. Due to the excellent performance, the VVC test model has adopted one implementation of the proposed scheme.

cs.MM↗

arXiv2020

Spatial Language Representation with Multi-Level Geocoding

We present a multi-level geocoding model (MLG) that learns to associate texts to geographic locations. The Earth's surface is represented using space-filling curves that decompose the sphere into a hierarchy of similarly sized, non-overlapping cells. MLG balances generalization and accuracy by combining losses across multiple levels and predicting cells at each level simultaneously. Without using any dataset-specific tuning, we show that MLG obtains state-of-the-art results for toponym resolution on three English datasets. Furthermore, it obtains large gains without any knowledge base metadata, demonstrating that it can effectively learn the connection between text spans and coordinates - and thus can be extended to toponymns not present in knowledge bases.

cs.CL↗

arXiv2020

Zero-Shot Heterogeneous Transfer Learning from Recommender Systems to Cold-Start Search Retrieval

Many recent advances in neural information retrieval models, which predict top-K items given a query, learn directly from a large training set of (query, item) pairs. However, they are often insufficient when there are many previously unseen (query, item) combinations, often referred to as the cold start problem. Furthermore, the search system can be biased towards items that are frequently shown to a query previously, also known as the 'rich get richer' (a.k.a. feedback loop) problem. In light of these problems, we observed that most online content platforms have both a search and a recommender system that, while having heterogeneous input spaces, can be connected through their common output item space and a shared semantic representation. In this paper, we propose a new Zero-Shot Heterogeneous Transfer Learning framework that transfers learned knowledge from the recommender system component to improve the search component of a content platform. First, it learns representations of items and their natural-language features by predicting (item, item) correlation graphs derived from the recommender system as an auxiliary task. Then, the learned representations are transferred to solve the target search retrieval task, performing query-to-item prediction without having seen any (query, item) pairs in training. We conduct online and offline experiments on one of the world's largest search and recommender systems from Google, and present the results and lessons learned. We demonstrate that the proposed approach can achieve high performance on offline search retrieval tasks, and more importantly, achieved significant improvements on relevance and user interactions over the highly-optimized production system in online experiments.

cs.LG↗

arXiv2020

Improving Semantic Segmentation via Decoupled Body and Edge Supervision

Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for semantic segmentation is proposed. Our insight is that appealing performance of semantic segmentation requires \textit{explicitly} modeling the object \textit{body} and \textit{edge}, which correspond to the high and low frequency of the image. To do so, we first warp the image feature by learning a flow field to make the object part more consistent. The resulting body feature and the residual edge feature are further optimized under decoupled supervision by explicitly sampling different parts (body or edge) pixels. We show that the proposed framework with various baselines or backbone networks leads to better object inner consistency and object boundaries. Extensive experiments on four major road scene semantic segmentation benchmarks including \textit{Cityscapes}, \textit{CamVid}, \textit{KIITI} and \textit{BDD} show that our proposed approach establishes new state of the art while retaining high efficiency in inference. In particular, we achieve 83.7 mIoU \% on Cityscape with only fine-annotated data. Code and models are made available to foster any further research (\url{https://github.com/lxtGH/DecoupleSegNets}).

cs.CV↗

arXiv2020

Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation

In many fields, self-supervised learning solutions are rapidly evolving and filling the gap with supervised approaches. This fact occurs for depth estimation based on either monocular or stereo, with the latter often providing a valid source of self-supervision for the former. In contrast, to soften typical stereo artefacts, we propose a novel self-supervised paradigm reversing the link between the two. Purposely, in order to train deep stereo networks, we distill knowledge through a monocular completion network. This architecture exploits single-image clues and few sparse points, sourced by traditional stereo algorithms, to estimate dense yet accurate disparity maps by means of a consensus mechanism over multiple estimations. We thoroughly evaluate with popular stereo datasets the impact of different supervisory signals showing how stereo networks trained with our paradigm outperform existing self-supervised frameworks. Finally, our proposal achieves notable generalization capabilities dealing with domain shift issues. Code available at https://github.com/FilippoAleotti/Reversing

cs.CV↗

arXiv2020

NPU Speaker Verification System for INTERSPEECH 2020 Far-Field Speaker Verification Challenge

This paper describes the NPU system submitted to Interspeech 2020 Far-Field Speaker Verification Challenge (FFSVC). We particularly focus on far-field text-dependent SV from single (task1) and multiple microphone arrays (task3). The major challenges in such scenarios are short utterance and cross-channel and distance mismatch for enrollment and test. With the belief that better speaker embedding can alleviate the effects from short utterance, we introduce a new speaker embedding architecture - ResNet-BAM, which integrates a bottleneck attention module with ResNet as a simple and efficient way to further improve the representation power of ResNet. This contribution brings up to 1% EER reduction. We further address the mismatch problem in three directions. First, domain adversarial training, which aims to learn domain-invariant features, can yield to 0.8% EER reduction. Second, front-end signal processing, including WPE and beamforming, has no obvious contribution, but together with data selection and domain adversarial training, can further contribute to 0.5% EER reduction. Finally, data augmentation, which works with a specifically-designed data selection strategy, can lead to 2% EER reduction. Together with the above contributions, in the middle challenge results, our single submission system (without multi-system fusion) achieves the first and second place on task 1 and task 3, respectively.

eess.AS↗

arXiv2020

Few-shot Action Recognition with Permutation-invariant Attention

Many few-shot learning models focus on recognising images. In contrast, we tackle a challenging task of few-shot action recognition from videos. We build on a C3D encoder for spatio-temporal video blocks to capture short-range action patterns. Such encoded blocks are aggregated by permutation-invariant pooling to make our approach robust to varying action lengths and long-range temporal dependencies whose patterns are unlikely to repeat even in clips of the same class. Subsequently, the pooled representations are combined into simple relation descriptors which encode so-called query and support clips. Finally, relation descriptors are fed to the comparator with the goal of similarity learning between query and support clips. Importantly, to re-weight block contributions during pooling, we exploit spatial and temporal attention modules and self-supervision. In naturalistic clips (of the same class) there exists a temporal distribution shift--the locations of discriminative temporal action hotspots vary. Thus, we permute blocks of a clip and align the resulting attention regions with similarly permuted attention regions of non-permuted clip to train the attention mechanism invariant to block (and thus long-term hotspot) permutations. Our method outperforms the state of the art on the HMDB51, UCF101, miniMIT datasets.

cs.CV↗

arXiv2020

Learning-based Computer-aided Prescription Model for Parkinson's Disease: A Data-driven Perspective

In this paper, we study a novel problem: "automatic prescription recommendation for PD patients." To realize this goal, we first build a dataset by collecting 1) symptoms of PD patients, and 2) their prescription drug provided by neurologists. Then, we build a novel computer-aided prescription model by learning the relation between observed symptoms and prescription drug. Finally, for the new coming patients, we could recommend (predict) suitable prescription drug on their observed symptoms by our prescription model. From the methodology part, our proposed model, namely Prescription viA Learning lAtent Symptoms (PALAS), could recommend prescription using the multi-modality representation of the data. In PALAS, a latent symptom space is learned to better model the relationship between symptoms and prescription drug, as there is a large semantic gap between them. Moreover, we present an efficient alternating optimization method for PALAS. We evaluated our method using the data collected from 136 PD patients at Nanjing Brain Hospital, which can be regarded as a large dataset in PD research community. The experimental results demonstrate the effectiveness and clinical potential of our method in this recommendation task, if compared with other competing methods.

cs.LG↗

arXiv2020

A novel deep learning-based method for monochromatic image synthesis from spectral CT using photon-counting detectors

With the growing technology of photon-counting detectors (PCD), spectral CT is a widely concerned topic which has the potential of material differentiation. However, due to some non-ideal factors such as cross talk and pulse pile-up of the detectors, direct reconstruction from detected spectrum without any corrections will get a wrong result. Conventional methods try to model these factors using calibration and make corrections accordingly, but depend on the preciseness of the model. To solve this problem, in this paper, we proposed a novel deep learning-based monochromatic image synthesis method working in sinogram domain. Different from previous deep learning-based methods aimed at this problem, we designed a novel network architecture according to the physical model of cross talk, and it can solve this problem better in an ingenious way. Our method was tested on a cone-beam CT (CBCT) system equipped with a PCD. After using FDK algorithm on the corrected projection, we got quite more accurate results with less noise, which showed the feasibility of monochromatic image synthesis by our method.

physics.med-ph↗

arXiv2020

XingGAN for Person Image Generation

We propose a novel Generative Adversarial Network (XingGAN or CrossingGAN) for person image generation tasks, i.e., translating the pose of a given person to a desired one. The proposed Xing generator consists of two generation branches that model the person's appearance and shape information, respectively. Moreover, we propose two novel blocks to effectively transfer and update the person's shape and appearance embeddings in a crossing way to mutually improve each other, which has not been considered by any other existing GAN-based image generation work. Extensive experiments on two challenging datasets, i.e., Market-1501 and DeepFashion, demonstrate that the proposed XingGAN advances the state-of-the-art performance both in terms of objective quantitative scores and subjective visual realness. The source code and trained models are available at https://github.com/Ha0Tang/XingGAN.

cs.CV↗

arXiv2020

FeCAM: A Universal Compact Digital and Analog Content Addressable Memory Using Ferroelectric

Ferroelectric field effect transistors (FeFETs) are being actively investigated with the potential for in-memory computing (IMC) over other non-volatile memories (NVMs). Content Addressable Memories (CAMs) are a form of IMC that performs parallel searches for matched entries over a memory array for a given input query. CAMs are widely used for data-centric applications that involve pattern matching and search functionality. To accommodate the ever expanding data, it is attractive to resort to analog CAM for memory density improvement. However, the digital CAM design nowadays based on standard CMOS or emerging nonvolatile memories (e.g., resistive storage devices) is already challenging due to area, power, and cost penalties. Thus, it can be extremely expensive to achieve analog CAM with those technologies due to added cell components. As such, we propose, for the first time, a universal compact FeFET based CAM design, FeCAM, with search and storage functionality enabled in digital and analog domain simultaneously. By exploiting the multi-level-cell (MLC) states of FeFET, FeCAM can store and search inputs in either digital or analog domain. We perform a device-circuit co-design of the proposed FeCAM and validate its functionality and performance using an experimentally calibrated FeFET model. Circuit level simulation results demonstrate that FeCAM can either store continuous matching ranges or encode 3-bit data in a single CAM cell. When compared with the existing digital CMOS based CAM approaches, FeCAM is found to improve both memory density by 22.4X and energy saving by 8.6/3.2X for analog/digital modes, respectively. In the CAM-related application, our evaluations show that FeCAM can achieve 60.5X/23.1X saving in area/search energy compared with conventional CMOS based CAMs.

cs.ET↗

arXiv2020

Egocentric Action Recognition by Video Attention and Temporal Context

We present the submission of Samsung AI Centre Cambridge to the CVPR2020 EPIC-Kitchens Action Recognition Challenge. In this challenge, action recognition is posed as the problem of simultaneously predicting a single `verb' and `noun' class label given an input trimmed video clip. That is, a `verb' and a `noun' together define a compositional `action' class. The challenging aspects of this real-life action recognition task include small fast moving objects, complex hand-object interactions, and occlusions. At the core of our submission is a recently-proposed spatial-temporal video attention model, called `W3' (`What-Where-When') attention~\cite{perez2020knowing}. We further introduce a simple yet effective contextual learning mechanism to model `action' class scores directly from long-term temporal behaviour based on the `verb' and `noun' prediction scores. Our solution achieves strong performance on the challenge metrics without using object-specific reasoning nor extra training data. In particular, our best solution with multimodal ensemble achieves the 2$^{nd}$ best position for `verb', and 3$^{rd}$ best for `noun' and `action' on the Seen Kitchens test set.

cs.CV↗

arXiv2020

PriceAggregator: An Intelligent System for Hotel Price Fetching

This paper describes the hotel price aggregation system - PriceAggregator, deployed at Agoda, a global online travel agency for hotels, vacation rentals, flights and airport transfer. Agoda aggregates non-direct suppliers' hotel rooms to ensure that Agoda's customers always have the widest selection of hotels, room types and packages. As of today, Agoda aggregates millions of hotels. The major challenge is that each supplier only allows Agoda to fetch for the hotel price with a limited amount of Queries Per Second (QPS). Due to the sheer volume of Agoda's user search traffic, this limited amount of QPS is never enough to cover all user searches. Inevitably, many user searches have to be ignored. Hence, booking lost. To overcome the challenge, we built PriceAggregator. PriceAggregator intelligently determines when, how and what to send to the suppliers to fetch for price. In this paper, we not only prove PriceAggregator is optimal theoretically but also demonstrate that PriceAggregator performs well in practice. PriceAggregator has been deployed in Agoda. Extensive online A/B experimentation have shown that PriceAggregator increases Agoda's bookings significantly.

cs.DC↗

arXiv2020

Self-supervised Video Object Segmentation

The objective of this paper is self-supervised representation learning, with the goal of solving semi-supervised video object segmentation (a.k.a. dense tracking). We make the following contributions: (i) we propose to improve the existing self-supervised approach, with a simple, yet more effective memory mechanism for long-term correspondence matching, which resolves the challenge caused by the dis-appearance and reappearance of objects; (ii) by augmenting the self-supervised approach with an online adaptation module, our method successfully alleviates tracker drifts caused by spatial-temporal discontinuity, e.g. occlusions or dis-occlusions, fast motions; (iii) we explore the efficiency of self-supervised representation learning for dense tracking, surprisingly, we show that a powerful tracking model can be trained with as few as 100 raw video clips (equivalent to a duration of 11mins), indicating that low-level statistics have already been effective for tracking tasks; (iv) we demonstrate state-of-the-art results among the self-supervised approaches on DAVIS-2017 and YouTube-VOS, as well as surpassing most of methods trained with millions of manual segmentation annotations, further bridging the gap between self-supervised and supervised learning. Codes are released to foster any further research (https://github.com/fangruizhu/self_sup_semiVOS).

cs.CV↗

arXiv2020

Neural Collaborative Filtering vs. Matrix Factorization Revisited

Embedding based models have been the state of the art in collaborative filtering for over a decade. Traditionally, the dot product or higher order equivalents have been used to combine two or more embeddings, e.g., most notably in matrix factorization. In recent years, it was suggested to replace the dot product with a learned similarity e.g. using a multilayer perceptron (MLP). This approach is often referred to as neural collaborative filtering (NCF). In this work, we revisit the experiments of the NCF paper that popularized learned similarities using MLPs. First, we show that with a proper hyperparameter selection, a simple dot product substantially outperforms the proposed learned similarities. Second, while a MLP can in theory approximate any function, we show that it is non-trivial to learn a dot product with an MLP. Finally, we discuss practical issues that arise when applying MLP based similarities and show that MLPs are too costly to use for item recommendation in production environments while dot products allow to apply very efficient retrieval algorithms. We conclude that MLPs should be used with care as embedding combiner and that dot products might be a better default choice.

cs.IR↗