BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Bo Hu

Bo Hu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer VisionMachine LearningArtificial Intelligenceastro-ph.GAeess.SPInformation Theorymath.ITeess.IVastro-ph.SRComputation and LanguageGraphicsHuman-Computer InteractionRobotics

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
18works
0followers
13topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

18 published item(s)

preprint2026arXiv

Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding

Video reasoning models are a core component of egocentric and embodied agents. However, standard benchmarks for assessing models provide only evaluation of the output (e.g. the answer to a question), without evaluation of intermediate reasoning steps, and most provide answers only in the text domain. We introduce Minerva-Ego, a benchmark for evaluating complex egocentric visual reasoning. We extend recent high-quality video data sources recorded from egocentric / embodied settings with a set of challenging, multi-step multimodal questions and spatiotemporally-dense human-annotated reasoning traces. Benchmarking experiments show that state-of-the-art models still have a large gap to human performance. To investigate this gap in detail, we annotate each reasoning trace in the dataset with the objects of interest required to solve the question, as spatiotemporal mask annotations. Through extensive evaluations, we identify that prompting frontier models with hints of 'where' and 'when' to look yields substantial improvements in performance. Minerva-Ego can be downloaded at https://github.com/google-deepmind/neptune.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

Olapa-MCoT: Enhancing the Chinese Mathematical Reasoning Capability of LLMs

CoT (Chain-of-Thought) is a way to solve reasoning problems for LLMs . Recently, many researches appear for improving the CoT capability of LLMs. In this work, we also proposed Olapa-MCoT, which is a LLMs based on llama2-13B PLM for finetuning and alignment learning. During the alignment training, we proposed the SimRRHF algorithm and Incorrect Data Relearning and mainly focused on optimizing the Chinese mathematical reasoning ability of Olapa-MCoT. The experiment achieved significant results, with the accuracy of Chinese mathematical reasoning up to 50%, 36% rise compared to llama2-13B. In addition, the accuracy of English reasoning ability also increased by nearly 4%.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Constraining Pseudo-label in Self-training Unsupervised Domain Adaptation with Energy-based Model

Deep learning is usually data starved, and the unsupervised domain adaptation (UDA) is developed to introduce the knowledge in the labeled source domain to the unlabeled target domain. Recently, deep self-training presents a powerful means for UDA, involving an iterative process of predicting the target domain and then taking the confident predictions as hard pseudo-labels for retraining. However, the pseudo-labels are usually unreliable, thus easily leading to deviated solutions with propagated errors. In this paper, we resort to the energy-based model and constrain the training of the unlabeled target sample with an energy function minimization objective. It can be achieved via a simple additional regularization or an energy-based loss. This framework allows us to gain the benefits of the energy-based model, while retaining strong discriminative performance following a plug-and-play fashion. The convergence property and its connection with classification expectation minimization are investigated. We deliver extensive experiments on the most popular and large-scale UDA benchmarks of image classification as well as semantic segmentation to demonstrate its generality and effectiveness.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Cross-domain Trajectory Prediction with CTP-Net

Most pedestrian trajectory prediction methods rely on a huge amount of trajectories annotation, which is time-consuming and expensive. Moreover, a well-trained model may not effectively generalize to a new scenario captured by another camera. Therefore, it is desirable to adapt the model trained on an annotated source domain to the target domain. To achieve domain adaptation for trajectory prediction, we propose a Cross-domain Trajectory Prediction Network (CTP-Net). In this framework, encoders are used in both domains to encode the observed trajectories, then their features are aligned by a cross-domain feature discriminator. Further, considering the consistency between the observed and the predicted trajectories, a target domain offset discriminator is utilized to adversarially regularize the future trajectory predictions to be in line with the observed trajectories. Extensive experiments demonstrate the effectiveness of our method on domain adaptation for pedestrian trajectory prediction.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Entry-Flipped Transformer for Inference and Prediction of Participant Behavior

Some group activities, such as team sports and choreographed dances, involve closely coupled interaction between participants. Here we investigate the tasks of inferring and predicting participant behavior, in terms of motion paths and actions, under such conditions. We narrow the problem to that of estimating how a set target participants react to the behavior of other observed participants. Our key idea is to model the spatio-temporal relations among participants in a manner that is robust to error accumulation during frame-wise inference and prediction. We propose a novel Entry-Flipped Transformer (EF-Transformer), which models the relations of participants by attention mechanisms on both spatial and temporal domains. Unlike typical transformers, we tackle the problem of error accumulation by flipping the order of query, key, and value entries, to increase the importance and fidelity of observed features in the current frame. Comparative experiments show that our EF-Transformer achieves the best performance on a newly-collected tennis doubles dataset, a Ceilidh dance dataset, and two pedestrian datasets. Furthermore, it is also demonstrated that our EF-Transformer is better at limiting accumulated errors and recovering from wrong estimations.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Information Theoretic Structured Generative Modeling

Rényi's information provides a theoretical foundation for tractable and data-efficient non-parametric density estimation, based on pair-wise evaluations in a reproducing kernel Hilbert space (RKHS). This paper extends this framework to parametric probabilistic modeling, motivated by the fact that Rényi's information can be estimated in closed-form for Gaussian mixtures. Based on this special connection, a novel generative model framework called the structured generative model (SGM) is proposed that makes straightforward optimization possible, because costs are scale-invariant, avoiding high gradient variance while imposing less restrictions on absolute continuity, which is a huge advantage in parametric information theoretic optimization. The implementation employs a single neural network driven by an orthonormal input appended to a single white noise source adapted to learn an infinite Gaussian mixture model (IMoG), which provides an empirically tractable model distribution in low dimensions. To train SGM, we provide three novel variational cost functions, based on Rényi's second-order entropy and divergence, to implement minimization of cross-entropy, minimization of variational representations of $f$-divergence, and maximization of the evidence lower bound (conditional probability). We test the framework for estimation of mutual information and compare the results with the mutual information neural estimation (MINE), for density estimation, for conditional probability estimation in Markov models as well as for training adversarial networks. Our preliminary results show that SGM significantly improves MINE estimation in terms of data efficiency and variance, conventional and variational Gaussian mixture models, as well as the performance of generative adversarial networks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

On the Provable Generalization of Recurrent Neural Networks

Recurrent Neural Network (RNN) is a fundamental structure in deep learning. Recently, some works study the training process of over-parameterized neural networks, and show that over-parameterized networks can learn functions in some notable concept classes with a provable generalization error bound. In this paper, we analyze the training and generalization for RNNs with random initialization, and provide the following improvements over recent works: 1) For a RNN with input sequence $x=(X_1,X_2,...,X_L)$, previous works study to learn functions that are summation of $f(β^T_lX_l)$ and require normalized conditions that $||X_l||\leqε$ with some very small $ε$ depending on the complexity of $f$. In this paper, using detailed analysis about the neural tangent kernel matrix, we prove a generalization error bound to learn such functions without normalized conditions and show that some notable concept classes are learnable with the numbers of iterations and samples scaling almost-polynomially in the input length $L$. 2) Moreover, we prove a novel result to learn N-variables functions of input sequence with the form $f(β^T[X_{l_1},...,X_{l_N}])$, which do not belong to the "additive" concept class, i,e., the summation of function $f(X_l)$. And we show that when either $N$ or $l_0=\max(l_1,..,l_N)-\min(l_1,..,l_N)$ is small, $f(β^T[X_{l_1},...,X_{l_N}])$ will be learnable with the number iterations and samples scaling almost-polynomially in the input length $L$.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Real-time Controllable Motion Transition for Characters

Real-time in-between motion generation is universally required in games and highly desirable in existing animation pipelines. Its core challenge lies in the need to satisfy three critical conditions simultaneously: quality, controllability and speed, which renders any methods that need offline computation (or post-processing) or cannot incorporate (often unpredictable) user control undesirable. To this end, we propose a new real-time transition method to address the aforementioned challenges. Our approach consists of two key components: motion manifold and conditional transitioning. The former learns the important low-level motion features and their dynamics; while the latter synthesizes transitions conditioned on a target frame and the desired transition duration. We first learn a motion manifold that explicitly models the intrinsic transition stochasticity in human motions via a multi-modal mapping mechanism. Then, during generation, we design a transition model which is essentially a sampling strategy to sample from the learned manifold, based on the target frame and the aimed transition duration. We validate our method on different datasets in tasks where no post-processing or offline computation is allowed. Through exhaustive evaluation and comparison, we show that our method is able to generate high-quality motions measured under multiple metrics. Our method is also robust under various target frames (with extreme cases).

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

A Risk-Sensitive Task Offloading Strategy for Edge Computing in Industrial Internet of Things

Edge computing has become one of the key enablers for ultra-reliable and low-latency communications in the industrial Internet of Things in the fifth generation communication systems, and is also a promising technology in the future sixth generation communication systems. In this work, we consider the application of edge computing to smart factories for mission-critical task offloading through wireless links. In such scenarios, although high end-to-end delays from the generation to completion of tasks happen with low probability, they may incur severe casualties and property loss, and should be seriously treated. Inspired by the risk management theory widely used in finance, we adopt the Conditional Value at Risk to capture the tail of the delay distribution. An upper bound of the Conditional Value at Risk is derived through analysis of the queues both at the devices and the edge computing servers. We aim to find out the optimal offloading policy taking into consideration both the average and the worst case delay performance of the system. Given that the formulated optimization problem is a non-convex mixed integer non-linear programming problem, a decomposition into sub-problems is performed and a two-stage heuristic algorithm is proposed. Simulation results validate our analysis and indicate that the proposed algorithm can reduce the risk in both the queuing and end-to-end delay.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Active Anomaly Detection with Switching Cost

The problem of detecting a single anomalous process among multiple independent processes is considered. Under a constraint on the number of processes that can be probed simultaneously, the decision maker should decide which processes to probe at each time and when to terminate the probing. Compared with previous work considering only the observation costs, the switching costs of switchings across processes also need to be taken into account in many practical scenarios. The objective is an active inference strategy that minimizes the Bayesian risk taking into account of the sample complexity, switching cost, as well as detection errors. Based on the framework of sequential design of experiments, we propose a low-complexity, low-switching deterministic policy for two scenarios where the total switching cost is negligible and the total switching cost is comparable to the total observation cost. We show that the proposed algorithm is asymptotically optimal in the former scenario and is order optimal in the latter scenario. Simulation results demonstrate strong performance in the finite regime for both scenarios.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Energy-constrained Self-training for Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) aims to transfer the knowledge on a labeled source domain distribution to perform well on an unlabeled target domain. Recently, the deep self-training involves an iterative process of predicting on the target domain and then taking the confident predictions as hard pseudo-labels for retraining. However, the pseudo-labels are usually unreliable, and easily leading to deviated solutions with propagated errors. In this paper, we resort to the energy-based model and constrain the training of the unlabeled target sample with the energy function minimization objective. It can be applied as a simple additional regularization. In this framework, it is possible to gain the benefits of the energy-based model, while retaining strong discriminative performance following a plug-and-play fashion. We deliver extensive experiments on the most popular and large scale UDA benchmarks of image classification as well as semantic segmentation to demonstrate its generality and effectiveness.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Performance Analysis for Correlated AoI and Energy Efficiency in Heterogeneous CR-IoT System

We consider a cognitive radio based Internet of Things (CR-IoT) system where the secondary IoT device (SD) accesses the licensed channel during the transmission vacancies of the primary IoT device (PD). We focus on the impact of the IoT devices' heterogeneous traffic pattern on the energy efficiency and on the age of information (AoI) performance of the SD. We first derive closed-form expressions of the energy efficiency and the average AoI, and subsequently explore their convexity and monotonicity to the transmit power. Following these characterizations, an optimal transmit power optimization algorithm (TPOA) is proposed for the SD to maximize the energy efficiency while maintaining the average AoI under a predefined threshold. Numerical results verify the different preferences of the SD toward different PD traffic patterns, and provides insights into the tradeoff between the energy efficiency and the average AoI.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Regularized Recovery by Multi-order Partial Hypergraph Total Variation

Capturing complex high-order interactions among data is an important task in many scenarios. A common way to model high-order interactions is to use hypergraphs whose topology can be mathematically represented by tensors. Existing methods use a fixed-order tensor to describe the topology of the whole hypergraph, which ignores the divergence of different-order interactions. In this work, we take this divergence into consideration, and propose a multi-order hypergraph Laplacian and the corresponding total variation. Taking this total variation as a regularization term, we can utilize the topology information contained by it to smooth the hypergraph signal. This can help distinguish different-order interactions and represent high-order interactions accurately.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis

Recent advances in unsupervised domain adaptation (UDA) show that transferable prototypical learning presents a powerful means for class conditional alignment, which encourages the closeness of cross-domain class centroids. However, the cross-domain inner-class compactness and the underlying fine-grained subtype structure remained largely underexplored. In this work, we propose to adaptively carry out the fine-grained subtype-aware alignment by explicitly enforcing the class-wise separation and subtype-wise compactness with intermediate pseudo labels. Our key insight is that the unlabeled subtypes of a class can be divergent to one another with different conditional and label shifts, while inheriting the local proximity within a subtype. The cases of with or without the prior information on subtype numbers are investigated to discover the underlying subtype structure in an online fashion. The proposed subtype-aware dynamic UDA achieves promising results on medical diagnosis tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Surveys of Clumps, Cores, and Condensations in the Cygnus X: II. Radio Properties of the Massive Dense Cores

We have carried out a high-sensitivity and high-resolution radio continuum study towards a sample of 47 massive dense cores (MDCs) in the Cygnus X star-forming complex using the Karl G. Jansky Very Large Array, aiming to detect and characterize the radio emission associated with star-forming activities down to ~0.01 pc scales. We have detected 64 radio sources within or closely around the full width at half-maximum (FWHM) of the MDCs, of which 37 are reported for the first time. The majority of the detected radio sources are associated with dust condensations embedded within the MDCs, and they are mostly weak and compact. We are able to build spectral energy distributions for 8 sources. Two of them indicate non-thermal emission and the other six indicate thermal free-free emission. We have determined that most of the radio sources are ionized jets or winds originating from massive young stellar objects, whereas only a few sources are likely to be ultra-compact HII regions. Further quantitative analyses indicate that the radio luminosity of the detected radio sources increases along the evolution path of the MDCs.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

DR 21 South Filament: a Parsec-sized Dense Gas Accretion Flow onto the DR 21 Massive Young Cluster

DR21 south filament (DR21SF) is a unique component of the giant network of filamentary molecular clouds in the north region of Cygnus X complex. Unlike the highly fragmented and star-forming active environment it resides, DR21SF exhibits a coherent profile in the column density map with very few star formation signposts, even though the previously reported linear density of the filament is an order of magnitude higher than the thermal stable threshold. We derive the size (3.6~pc by 0.13~pc), temperature (10 to 15~K), and mass (1048~\textit{M$_\odot$}) of DR21SF from Shanghai 65 m TianMa Radio Telescope (TMRT) observations of NH$_3$ (1, 1) and (2, 2) inversion lines in conjunction with the column density map from our previous work. Star-forming sites are identified along the filament where gas temperature excesses. We find clear gradients in radial velocity and intrinsic line-width along the spine of the filament. The gradients can be well interpreted with a scenario of an accretion flow feeding DR 21 at a mass transfer rate of $1.1 \times 10^{-3}$~\textit{M$_\odot$} yr$^{-1}$. Based on the analysis of its kinematic temperature, intrinsic line-width and mass distribution, we conclude that DR21SF is in an overall trans-critical status, which indicates an early evolutionary stage.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Multiple outflows in the high-mass cluster forming region, G25.82-0.17

We present results of continuum and spectral line observations with ALMA and 22 GHz water (H$_2$O) maser observations using KaVA and VERA toward a high-mass star-forming region, G25.82-0.17. Multiple 1.3 mm continuum sources are revealed, indicating the presence of young stellar objects (YSOs) at different evolutionary stages, namely an ultra-compact HII region, G25.82-E, a high-mass young stellar object (HM-YSO), G25.82-W1, and starless cores, G25.82-W2 and G25.82-W3. Two SiO outflows, at N-S and SE-NW orientations, are identified. The CH$_3$OH 8$_{-1}$-7$_{0}$ E line, known to be a class I CH$_3$OH maser at 229 GHz is also detected showing a mixture of thermal and maser emission. Moreover, the H$_2$O masers are distributed in a region ~0.25" shifted from G25.82-W1. The CH$_3$OH 22$_{4}$-21$_{5}$ E line shows a compact ring-like structure at the position of G25.82-W1 with a velocity gradient, indicating a rotating disk or envelope. Assuming Keplerian rotation, the dynamical mass of G25.82-W1 is estimated to be $>$25 M$_{\odot}$ and the total mass of 20 M$_\odot$-84 M$_\odot$ is derived from the 1.3 mm continuum emission. The driving source of the N-S SiO outflow is G25.82-W1 while that of the SE-NW SiO outflow is uncertain. Detection of multiple high-mass starless$/$protostellar cores and candidates without low-mass cores implies that HM-YSOs could form in individual high-mass cores as predicted by the turbulent core accretion model. If this is the case, the high-mass star formation process in G25.82 would be consistent with a scaled-up version of low-mass star formation.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Fast Color-guided Depth Denoising for RGB-D Images by Graph Filtering

Depth images captured by off-the-shelf RGB-D cameras suffer from much stronger noise than color images. In this paper, we propose a method to denoise the depth images in RGB-D images by color-guided graph filtering. Our iterative method contains two components: color-guided similarity graph construction, and graph filtering on the depth signal. Implemented in graph vertex domain, filtering is accelerated as computation only occurs among neighboring vertices. Experimental results show that our method outperforms state-of-art depth image denoising methods significantly both on quality and efficiency.

0 citations0 reviewsNo code linkedOpen access