Searcharxiv⌕ Search

arXiv subjects

Haotian Zhang

Publications and source records attributed to Haotian Zhang.

At least 145 records · Page 8Linked to original sources
arXiv2023

M$^3$SC: A Generic Dataset for Mixed Multi-Modal (MMM) Sensing and Communication Integration

The sixth generation (6G) of mobile communication system is witnessing a new paradigm shift, i.e., integrated sensing-communication system. A comprehensive dataset is a prerequisite for 6G integrated sensing-communication research. This paper develops a novel simulation dataset, named M3SC, for mixed multi-modal (MMM) sensing-communication integration, and the generation framework of the M3SC dataset is further given. To obtain multi-modal sensory data in physical space and communication data in electromagnetic space, we utilize AirSim and WaveFarer to collect multi-modal sensory data and exploit Wireless InSite to collect communication data. Furthermore, the in-depth integration and precise alignment of AirSim, WaveFarer, and Wireless InSite are achieved. The M3SC dataset covers various weather conditions, various frequency bands, and different times of the day. Currently, the M3SC dataset contains 1500 snapshots, including 80 RGB images, 160 depth maps, 80 LiDAR point clouds, 256 sets of mmWave waveforms with 8 radar point clouds, and 72 channel impulse response (CIR) matrices per snapshot, thus totaling 120,000 RGB images, 240,000 depth maps, 120,000 LiDAR point clouds, 384,000 sets of mmWave waveforms with 12,000 radar point clouds, and 108,000 CIR matrices. The data processing result presents the multi-modal sensory information and communication channel statistical properties. Finally, the MMM sensing-communication application, which can be supported by the M3SC dataset, is discussed.

eess.SP↗
arXiv2023

Breaking the Curse of Quality Saturation with User-Centric Ranking

A key puzzle in search, ads, and recommendation is that the ranking model can only utilize a small portion of the vastly available user interaction data. As a result, increasing data volume, model size, or computation FLOPs will quickly suffer from diminishing returns. We examined this problem and found that one of the root causes may lie in the so-called ``item-centric'' formulation, which has an unbounded vocabulary and thus uncontrolled model complexity. To mitigate quality saturation, we introduce an alternative formulation named ``user-centric ranking'', which is based on a transposed view of the dyadic user-item interaction data. We show that this formulation has a promising scaling property, enabling us to train better-converged models on substantially larger data sets.

cs.IR↗
arXiv2023

Infinite Physical Monkey: Do Deep Learning Methods Really Perform Better in Conformation Generation?

Conformation Generation is a fundamental problem in drug discovery and cheminformatics. And organic molecule conformation generation, particularly in vacuum and protein pocket environments, is most relevant to drug design. Recently, with the development of geometric neural networks, the data-driven schemes have been successfully applied in this field, both for molecular conformation generation (in vacuum) and binding pose generation (in protein pocket). The former beats the traditional ETKDG method, while the latter achieves similar accuracy compared with the widely used molecular docking software. Although these methods have shown promising results, some researchers have recently questioned whether deep learning (DL) methods perform better in molecular conformation generation via a parameter-free method. To our surprise, what they have designed is some kind analogous to the famous infinite monkey theorem, the monkeys that are even equipped with physics education. To discuss the feasibility of their proving, we constructed a real infinite stochastic monkey for molecular conformation generation, showing that even with a more stochastic sampler for geometry generation, the coverage of the benchmark QM-computed conformations are higher than those of most DL-based methods. By extending their physical monkey algorithm for binding pose prediction, we also discover that the successful docking rate also achieves near-best performance among existing DL-based docking models. Thus, though their conclusions are right, their proof process needs more concern.

q-bio.BM↗
arXiv2023

Evidence of high-temperature exciton condensation in a two-dimensional semimetal

Electrons and holes can spontaneously form excitons and condense in a semimetal or semiconductor, as predicted decades ago. This type of Bose condensation can happen at much higher temperatures in comparison with dilute atomic gases. Two-dimensional (2D) materials with reduced Coulomb screening around the Fermi level are promising for realizing such a system. Here we report a change in the band structure accompanied by a phase transition at about 180 K in single-layer ZrTe2 based on angle-resolved photoemission spectroscopy (ARPES) measurements. Below the transition temperature, gap opening and development of an ultra-flat band top around the zone center are observed. This gap and the phase transition are rapidly suppressed with extra carrier densities introduced by adding more layers or dopants on the surface. The results suggest the formation of an excitonic insulating ground state in single-layer ZrTe2, and the findings are rationalized by first principles calculations and a self-consistent mean-field theory. Our study provides evidence for exciton condensation in a 2D semimetal and demonstrates strong dimensionality effects on the formation of intrinsic bound electron-hole pairs in solids.

cond-mat.mes-hall↗
arXiv2022

Dynamical interplay between superconductivity and charge-density-wave: a nonlinear terahertz study of coherently-driven 2H-NbSe2 and La2-xSrxCuO4

2H-NbSe2 is an archetypal system in which superconductivity and charge-density-wave (CDW) coexist and compete macroscopically with each other. In particular, this interplay also manifests in their dynamical fluctuations. As a result, the superconducting amplitude fluctuations (i.e. Higgs mode) is pushed below the quasiparticle continuum, allowing it to become a coherent excitation observable by Raman scattering. In the present study, we coherently drive the collective oscillations of the two orders and visualize their interplay in the driven states in the time domain. We find that both collective modes contribute to terahertz third harmonic generation (THG) and the THG signals interfere below Tc, leading to an anti-resonance of the integrated THG signal. The dynamical Ginzburg-Landau model suggests that around the anti-resonance a periodic energy transfer between the driven Higgs oscillations and the driven CDW oscillations is possible. In addition to 2H-NbSe2, we also studied an underdoped La2-xSrxCuO4 (x ~ 0.12) driven beyond the perturbative regime of THG. A similar interference between two sources of THG is observed below Tc. While there might be additional sources of THG in these experiments, our results illustrate the roles of coupled modes in the terahertz THG process and the tantalizing possibility of coherent control via such couplings.

cond-mat.supr-con↗
arXiv2022

Nonmonontone submodular maximization under routing constraints

In machine learning and big data, the optimization objectives based on set-cover, entropy, diversity, influence, feature selection, etc. are commonly modeled as submodular functions. Submodular (function) maximization is generally NP-hard, even in the absence of constraints. Recently, submodular maximization has been successfully investigated for the settings where the objective function is monotone or the constraint is computation-tractable. However, maximizing nonmonotone submodular function with complex constraints is not yet well-understood. In this paper, we consider the nonmonotone submodular maximization with a cost budget or feasibility constraint (especially from route planning) that is generally NP-hard to evaluate. Such a problem is common for machine learning, big data, and robotics. This problem is NP-hard, and on top of that, its constraint evaluation is also NP-hard, which adds an additional layer of complexity. So far, few studies have been devoted to proposing effective solutions, making this problem currently unclear. In this paper, we first propose an iterated greedy algorithm, which yields an approximation solution. Then we develop the proof machinery that shows our algorithm is a bi-criterion approximation algorithm: it can achieve a constant-factor approximation to the optimal algorithm, while keeping the over-budget tightly bounded. We also explore practical considerations of achieving a trade-off between time complexity and over-budget. Finally, we conduct numeric experiments on two concrete examples, and show our design's efficacy in practical settings.

cs.DS↗
arXiv2022

Innovative Drug-like Molecule Generation from Flow-based Generative Model

To design a drug given a biological molecule by using deep learning methods, there are many successful models published recently. People commonly used generative models to design new molecules given certain protein. LiGAN was regarded as the baseline of deep learning model which was developed on convolutional neural networks. Recently, GraphBP showed its ability to predict innovative "real" chemicals that the binding affinity outperformed with traditional molecular docking methods by using a flow-based generative model with a graph neural network and multilayer perception. However, all those methods regarded proteins as rigid bodies and only include a very small part of proteins related to binding. However, the dynamics of proteins are essential for drug binding. Based on GraphBP, we proposed to generate more solid work derived from protein data bank. The results will be evaluated by validity and binding affinity by using a computational chemistry algorithm.

cs.LG↗
arXiv2022

GLIPv2: Unifying Localization and Vision-Language Understanding

We present GLIPv2, a grounded VL understanding model, that serves both localization tasks (e.g., object detection, instance segmentation) and Vision-Language (VL) understanding tasks (e.g., VQA, image captioning). GLIPv2 elegantly unifies localization pre-training and Vision-Language Pre-training (VLP) with three pre-training tasks: phrase grounding as a VL reformulation of the detection task, region-word contrastive learning as a novel region-word level contrastive learning task, and the masked language modeling. This unification not only simplifies the previous multi-stage VLP procedure but also achieves mutual benefits between localization and understanding tasks. Experimental results show that a single GLIPv2 model (all model weights are shared) achieves near SoTA performance on various localization and understanding tasks. The model also shows (1) strong zero-shot and few-shot adaption performance on open-vocabulary object detection tasks and (2) superior grounding capability on VL understanding tasks. Code will be released at https://github.com/microsoft/GLIP.

cs.CV↗
arXiv2022

APGKT: Exploiting Associative Path on Skills Graph for Knowledge Tracing

Knowledge tracing (KT) is a fundamental task in educational data mining that mainly focuses on students' dynamic cognitive states of skills. The question-answering process of students can be regarded as a thinking process that considers the following two problems. One problem is which skills are needed to answer the question, and the other is how to use these skills in order. If a student wants to answer a question correctly, the student should not only master the set of skills involved in the question but also think and obtain the associative path on the skills graph. The nodes in the associative path refer to the skills needed and the path shows the order of using them. The associative path is referred to as the skill mode. Thus, obtaining the skill modes is the key to answering questions successfully. However, most existing KT models only focus on a set of skills, without considering the skill modes. We propose a KT model, called APGKT, that exploits skill modes. Specifically, we extract the subgraph topology of the skills involved in the question and combine the difficulty level of the skills to obtain the skill modes via encoding; then, through multi-layer recurrent neural networks, we obtain a student's higher-order cognitive states of skills, which is used to predict the student's future answering performance. Experiments on five benchmark datasets validate the effectiveness of the proposed model.

cs.CY↗
arXiv2022

COEM: Cross-Modal Embedding for MetaCell Identification

Metacells are disjoint and homogeneous groups of single-cell profiles, representing discrete and highly granular cell states. Existing metacell algorithms tend to use only one modality to infer metacells, even though single-cell multi-omics datasets profile multiple molecular modalities within the same cell. Here, we present \textbf{C}ross-M\textbf{O}dal \textbf{E}mbedding for \textbf{M}etaCell Identification (COEM), which utilizes an embedded space leveraging the information of both scATAC-seq and scRNA-seq to perform aggregation, balancing the trade-off between fine resolution and sufficient sequencing coverage. COEM outperforms the state-of-the-art method SEACells by efficiently identifying accurate and well-separated metacells across datasets with continuous and discrete cell types. Furthermore, COEM significantly improves peak-to-gene association analyses, and facilitates complex gene regulatory inference tasks.

q-bio.GN↗
arXiv2022

Sobolev Training for Implicit Neural Representations with Approximated Image Derivatives

Recently, Implicit Neural Representations (INRs) parameterized by neural networks have emerged as a powerful and promising tool to represent different kinds of signals due to its continuous, differentiable properties, showing superiorities to classical discretized representations. However, the training of neural networks for INRs only utilizes input-output pairs, and the derivatives of the target output with respect to the input, which can be accessed in some cases, are usually ignored. In this paper, we propose a training paradigm for INRs whose target output is image pixels, to encode image derivatives in addition to image values in the neural network. Specifically, we use finite differences to approximate image derivatives. We show how the training paradigm can be leveraged to solve typical INRs problems, i.e., image regression and inverse rendering, and demonstrate this training paradigm can improve the data-efficiency and generalization capabilities of INRs. The code of our method is available at \url{https://github.com/megvii-research/Sobolev_INRs}.

cs.CV↗
arXiv2022

Spotting Temporally Precise, Fine-Grained Events in Video

We introduce the task of spotting temporally precise, fine-grained events in video (detecting the precise moment in time events occur). Precise spotting requires models to reason globally about the full-time scale of actions and locally to identify subtle frame-to-frame appearance and motion differences that identify events during these actions. Surprisingly, we find that top performing solutions to prior video understanding tasks such as action detection and segmentation do not simultaneously meet both requirements. In response, we propose E2E-Spot, a compact, end-to-end model that performs well on the precise spotting task and can be trained quickly on a single GPU. We demonstrate that E2E-Spot significantly outperforms recent baselines adapted from the video action detection, segmentation, and spotting literature to the precise spotting task. Finally, we contribute new annotations and splits to several fine-grained sports action datasets to make these datasets suitable for future work on precise spotting.

cs.CV↗
arXiv2022

Grounded Language-Image Pre-training

This paper presents a grounded language-image pre-training (GLIP) model for learning object-level, language-aware, and semantic-rich visual representations. GLIP unifies object detection and phrase grounding for pre-training. The unification brings two benefits: 1) it allows GLIP to learn from both detection and grounding data to improve both tasks and bootstrap a good grounding model; 2) GLIP can leverage massive image-text pairs by generating grounding boxes in a self-training fashion, making the learned representation semantic-rich. In our experiments, we pre-train GLIP on 27M grounding data, including 3M human-annotated and 24M web-crawled image-text pairs. The learned representations demonstrate strong zero-shot and few-shot transferability to various object-level recognition tasks. 1) When directly evaluated on COCO and LVIS (without seeing any images in COCO during pre-training), GLIP achieves 49.8 AP and 26.9 AP, respectively, surpassing many supervised baselines. 2) After fine-tuned on COCO, GLIP achieves 60.8 AP on val and 61.5 AP on test-dev, surpassing prior SoTA. 3) When transferred to 13 downstream object detection tasks, a 1-shot GLIP rivals with a fully-supervised Dynamic Head. Code is released at https://github.com/microsoft/GLIP.

cs.CV↗
arXiv2022

MegLoc: A Robust and Accurate Visual Localization Pipeline

In this paper, we present a visual localization pipeline, namely MegLoc, for robust and accurate 6-DoF pose estimation under varying scenarios, including indoor and outdoor scenes, different time across a day, different seasons across a year, and even across years. MegLoc achieves state-of-the-art results on a range of challenging datasets, including winning the Outdoor and Indoor Visual Localization Challenge of ICCV 2021 Workshop on Long-term Visual Localization under Changing Conditions, as well as the Re-localization Challenge for Autonomous Driving of ICCV 2021 Workshop on Map-based Localization for Autonomous Driving.

cs.CV↗
arXiv2022

Analyzing Who and What Appears in a Decade of US Cable TV News

Cable TV news reaches millions of U.S. households each day, meaning that decisions about who appears on the news and what stories get covered can profoundly influence public opinion and discourse. We analyze a data set of nearly 24/7 video, audio, and text captions from three U.S. cable TV networks (CNN, FOX, and MSNBC) from January 2010 to July 2019. Using machine learning tools, we detect faces in 244,038 hours of video, label each face's presented gender, identify prominent public figures, and align text captions to audio. We use these labels to perform screen time and word frequency analyses. For example, we find that overall, much more screen time is given to male-presenting individuals than to female-presenting individuals (2.4x in 2010 and 1.9x in 2019). We present an interactive web-based tool, accessible at https://tvnews.stanford.edu, that allows the general public to perform their own analyses on the full cable TV news data set.

cs.CY↗
arXiv2021

Forecasting battery capacity and power degradation with multi-task learning

Lithium-ion batteries degrade due to usage and exposure to environmental conditions, which affects their capability to store energy and supply power. Accurately predicting the capacity and power fade of lithium-ion battery cells is challenging due to intrinsic manufacturing variances and coupled nonlinear ageing mechanisms. In this paper, we propose a data-driven prognostics framework to predict both capacity and power fade simultaneously with multi-task learning. The model is able to predict the degradation trajectory of both capacity and internal resistance together with knee-points and end-of-life points accurately at early-life stage. The validation shows an average percentage error of 2.37% and 1.24% for the prediction of capacity fade and resistance rise, respectively. The model's ability to accurately predict the degradation, facing capacity and resistance estimation errors, further demonstrates the model's robustness and generalizability. Compared with single-task learning models for forecasting capacity and power degradation, the model shows a significant prediction accuracy improvement and computational cost reduction. This work presents the highlights of multi-task learning in the degradation prognostics for lithium-ion batteries.

eess.SY↗
arXiv2021

TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers

In this paper, we present TransMVSNet, based on our exploration of feature matching in multi-view stereo (MVS). We analogize MVS back to its nature of a feature matching task and therefore propose a powerful Feature Matching Transformer (FMT) to leverage intra- (self-) and inter- (cross-) attention to aggregate long-range context information within and across images. To facilitate a better adaptation of the FMT, we leverage an Adaptive Receptive Field (ARF) module to ensure a smooth transit in scopes of features and bridge different stages with a feature pathway to pass transformed features and gradients across different scales. In addition, we apply pair-wise feature correlation to measure similarity between features, and adopt ambiguity-reducing focal loss to strengthen the supervision. To the best of our knowledge, TransMVSNet is the first attempt to leverage Transformer into the task of MVS. As a result, our method achieves state-of-the-art performance on DTU dataset, Tanks and Temples benchmark, and BlendedMVS dataset. The code of our method will be made available at https://github.com/MegviiRobot/TransMVSNet .

cs.CV↗