Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks277 from public data
- Compressive data gathering for large-scale wireless sensor networks628
This paper presents the first complete design to apply compressive sampling theory to sensor data gathering for large-scale wireless sensor networks and shows the efficiency and robustness of the proposed scheme.
- 451
- 346
- An Iterative BP-CNN Architecture for Channel Decoding294
A novel iterative belief propagation – convolutional neural network (BP-CNN) architecture for channel decoding under correlated noise that concatenates a trained CNN with a standard BP decoder and the introduction of the normality test to the CNN training shapes the residual noise distribution.
- 286
- Towards Optimal Power Control via Ensembling Deep Neural Networks275
Simulation results show that for the standard symmetric $K$ -user Gaussian interference channel, the proposed methods can outperform state-of-the-art power control solutions under a variety of system configurations.
- VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows271
This work proposes a large-scale Visible-Event benchmark (termed VisEvent) and builds a simple but effective tracking algorithm by proposing a cross-modality transformer, to achieve more effective feature fusion between visible and event data.
- 239
- Disentangle Your Dense Object Detector234
This paper investigates three important conjunctions of dense detectors and proposes Disentangled Dense Object Detector (DDOD), in which simple and effective disentanglement mechanisms are designed and integrated into the current state-of-the-art dense object detectors.
- 221
- Dual-camera design for coded aperture snapshot spectral imaging214
A beam splitter is placed in front of the objective lens of CASSI, which allows the same scene to be simultaneously captured by a grayscale camera, which greatly eases the reconstruction problem and yields high-quality 3D spectral data.
- 209
- Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs166
TACT is inspired by the observation that the semantic correlation between two relations is highly correlated to their topological structure in knowledge graphs and categorizes all relation pairs into several topological patterns, and proposes a Relational Correlation Network (RCN) to learn the importance of the different patterns for inductive link prediction.
- Online planning for multi-agent systems with bounded communication135
An online algorithm for planning under uncertainty in multi-agent settings modeled as DEC-POMDPs that can solve problems that are too large for the best existing offline planning algorithms and it outperforms the best online method, producing much higher value with much less communication in most cases.
- 134
- 126
- 122
- A Disaster Response System based on Human-Agent Collectives111
HAC-ER demonstrates how such Human-Agent Collectives (HACs) can address key challenges in disaster response and utilises crowdsourcing combined with machine learning to obtain most important situational awareness from large streams of reports posted by members of the public and trusted organisations.
- Decoding and mapping task states of the human brain via deep learning100
Without incurring the burden of handcrafting the features, the proposed deep decoding method can classify brain task states highly accurately, and is a powerful tool for fMRI researchers.
- Action Unit Memory Network for Weakly Supervised Temporal Action Localization99
This paper presents an Action Unit Memory Network (AUMN) for weakly supervised temporal action localization, which can mitigate the above two challenges by learning an action unit memory bank.
- Human–agent collaboration for disaster response99
This paper develops an algorithm, based on a multi-agent Markov decision process representation of the task allocation problem and shows that it outperforms standard baseline solutions and integrates it into a planning agent that responds to requests for tasks from participants in a mixed-reality location-based game that simulates disaster response settings in the real-world.
- Rethinking Graph Convolutional Networks in Knowledge Graph Completion96
It is suggested that existing GCNs are unnecessary for KGC, and novel GCN-based KGC models should count on more ablation studies to validate their effectiveness.
- Distributed multi-view video coding92
A practical framework of distributed multi-view video coding, in which inter-camera communication is avoided and the large computing complexity is moved from encoder to decoder, and the traditional inter frame is replaced by Wyner-Ziv frame.
- A Two-Stream Mutual Attention Network for Semi-Supervised Biomedical Segmentation with Noisy Labels87
A Two-Stream Mutual Attention Network (TSMAN) that weakens the influence of back-propagated gradients caused by incorrect labels, thereby rendering the network robust to unclean data.
- Unambiguous 3D measurement from speckle-embedded fringe85
A novel phase-shifting method for fast, accurate, and unambiguous 3D shape measurement by embedding a speckle-like signal in three sinusoidal fringe patterns to eliminate the phase ambiguity, but without reducing the fringe amplitude or frequency.
- 84
- 80
- 79
- 78
- Feudal Multi-Agent Deep Reinforcement Learning for Traffic Signal Control77
This work borrows ideas from feudal RL and proposes a novel MARL approach combining with the feudal hierarchy for traffic signal control, which outperforms the state-of-the-art in almost all evaluation metrics commonly used for traffic signal control.
- Scalable volumetric imaging for ultrahigh-speed brain mapping at synaptic resolution76
A new light-sheet microscopy method for fast, large-scale volumetric imaging that achieves high-speed 3D image acquisition of an entire mouse brain within 2 hours, at a resolution capable of resolving synaptic spines is described.
- Seamless rate adaptation for wireless networking76
This paper designs a Seamless Rate Adaptation for wireless networking which achieves smooth rate adjustment in a broad dynamic range of channel conditions and proposes rate compatible modulation (RCM), in which modulation signals are incrementally generated from information bits through weighted mapping.
- HIPA: Hierarchical Patch Transformer for Single Image Super Resolution73
A HIPA is presented, which stands for a novel Transformer architecture that progressively recovers the high resolution image using a hierarchical patch partition and a new attention-based position encoding scheme for Transformer is proposed to let the network focus on which tokens should be paid more attention.
- 73
- 72
- Online planning for ad hoc autonomous agent teams71
This work proposes a novel online planning algorithm for ad hoc team settings--challenging situations in which an agent must collaborate with unknown teammates without prior coordination and establishes analytically the convergence of the algorithm.
- 70
- 67
- 65
- Compressing Deep Graph Neural Networks via Adversarial Knowledge Distillation64
A novel Adversarial Knowledge Distillation framework for graph models named GraphAKD is proposed, which adversarially trains a discriminator and a generator to adaptively detect and decrease the discrepancy between teacher and student networks.
- 64
- 64
- 62
- 60
- 59
- 59
- 57
- 55
- 54
- 53
- 52
- Robots serve humans in public places— KeJia robot as a shopping assistant52
A novel multimodal interaction mechanism is designed by which customers can conveniently interact with the robot either in speech or via a mobile application, and the results of both simulated experiments and field tests confirm the feasibility, stability, and safety of the robot system.
- 51
- 49
- Adaptive Spot-Guided Transformer for Consistent Local Feature Matching48
This work proposes Adaptive Spot-Guided Transformer for local feature matching (ASTR), which jointly models the local consistency and scale variations in a unified coarse-to-fine architecture.
- Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation48
A background activation suppression (BAS) method designed to facilitate the learning of generator by suppressing the background activation value and which achieves state-of-the-art weakly supervised semantic segmentation performance on the PASCAL VOC 2012 and MS COCO 2014 datasets.
- Toward Effective Soft Robot Control via Reinforcement Learning47
This work designs an abstract representation of the state of soft robots and develops a reinforcement learning method to derive effective control policies, and demonstrates the effectiveness of the training method and its ability to produce good control policies under different conditions.
- A Study of Human-Agent Collaboration for Multi-UAV Task Allocation in Dynamic Environments47
A set of multi-UAV supervisory control interfaces and a multi-agent coordination algorithm to support human decision making in a setting where a team of humans oversee the coordination of multiple Unmanned Aerial Vehicles to perform a number of search tasks in dynamic environments that may cause the UAVs to drop out is developed.
- A study of human-agent collaboration for multi-UAV47
A set of multi-UAV supervisory control interfaces and a multi-agent coordination algorithm to support human decision making in a setting where a team of humans oversee the coordination of multiple Unmanned Aerial Vehicles to perform a number of search tasks in dynamic environments that may cause the UAVs to drop out is developed.
- Textured Image Demoiréing via Signal Decomposition and Guided Filtering46
A novel textured image demoiréing method by signal decomposition and guided filtering that outperforms the state-of-the-art methods for both synthetic and real images.
- Multi-Agent Online Planning with Communication46
An online algorithm for planning under uncertainty in multi-agent settings modeled as DEC-POMDPs that can solve problems that are too large for the best existing off-line planning algorithms and it outperforms the best online method, producing higher value with much less communication in most cases.
- 45
- 45
- 45
- 44
- 44
- 40
- 40
- Online Planning for Large Markov Decision Processes with Hierarchical Decomposition39
Compared to traditional online planning algorithms, MAXQ-OP is able to reach much more deeper states in the search tree with relatively less computation time by exploiting MAXQ hierarchical decomposition online.
- 38
- Leveraging Deep Statistics for Underwater Image Enhancement37
A convolutional neural network (CNN)-based framework to learn hierarchical statistical features related to color cast and contrast degradation and to leverage them for underwater image enhancement is proposed and achieves state-of-the-art performance.
- In‐the‐loop or on‐the‐loop? Interactional arrangements to support team coordination with a planning agent37
It is found that the human coordinator and the agent can successfully work together in most cases, with human coordinators inspecting and “correcting” the agent‐proposed plans.
- 37
- 36
- Visual summarization of web pages36
Since the internal image based summarization approach hardly works when the representative internal images are unavailable, a new strategy is proposed, which retrieves the representative image from the external to summarize the web page.
- 35
- 34
- 32
- 32
- Bayesian mixture modelling and inference based Thompson sampling in Monte-Carlo tree search31
This work presents a novel approach for MCTS using Bayesian mixture modeling and inference based Thompson sampling and applies it to the problem of online planning in MDPs, advancing the state-of-the-art UCT approach with better values on several benchmark problems.
- KeJia Robot–An Attractive Shopping Mall Guider30
This paper reports the project of a shopping mall guide robot, named KeJia, which is designed for customer navigation, information providing and entertainment in a real environment and demonstrates the stability, validity and feasibility of this robot system.
- 30
- Laser-Based People Detection and Obstacle Avoidance for a Hospital Transport Robot29
A novel deep learning-based method, which uses the deep neural network in a sliding window fashion to effectively classify every single point of a laser scan, is proposed, which runs in real-time and performs much better than traditional methods.
- 29
- 28
- 28
- 27
- 26
- 25
- 25
- 24
- Thompson Sampling Based Monte-Carlo Planning in POMDPs24
A novel online planning algorithm for large POMDPs using Thompson sampling based MCTS that balances between cumulative and simple regrets and outperforms the state-of-the-art approaches on several common benchmark problems.
- Compressive image broadcasting in MIMO systems with receiver antenna heterogeneity24
This work proposes a new analog image delivery system that adapts seamlessly along both dimensions of heterogeneity, and introduces a power allocation strategy to achieve a performance tradeoff between receivers with different antenna numbers.
- 24
- 24
- 23
- Monte-Carlo Tree Search for Scalable Coalition Formation23
A novel algorithm based on Monte-Carlo tree search for the problem of coalition structure generation (CSG) finds the optimal solution by sampling the coalition structure graph and incrementally expanding a search tree, which represents the partial space that has been searched.
- 23
- 23
- 22
- 22
- Coordinating human-UAV teams in disaster response21
This work considers a disaster response scenario where emergency responders have to complete rescue tasks in dynamic and uncertain environment with the assistance of multiple UAVs to collect information about the disaster space and proposes a novel online planning algorithm to solve this model.
- Multi-Agent Patrolling under Uncertainty and Threats21
This work forms the single-agent patrolling problem as a Partially Observable Markov Decision Process (POMDP) and proposes a computationally efficient algorithm to solve this model.
- 21
- 20
- SocialTrust: Enabling long-term social cooperation in peer-to-peer services20
This paper design and implement a social P2P network, named SocialTrust, based on peers’ common interests, and formally prove that the proposed distributed trust mechanism is secure and can defend against various forms of attacks.
- 20
- Accelerating Large Language Model Reasoning via Speculative Search19
A novel Speculative Search framework that significantly accelerates LLM reasoning by optimizing thought generation by utilizing a small model to strategically collaborate with a large model at both thought and token levels, efficiently generating high-quality reasoning thoughts.
- 19
- Appearance Prompt Vision Transformer for Connectome Reconstruction19
A coherent and unified Appearance Prompt Vision Transformer is proposed to integrate affinity and metric learning to exploit the complementarity by learning long-range spatial dependencies and achieves consistent improvements with huge flexibility under the same post-processing strategy.
- 19
- Fault tolerance in memristive crossbar-based neuromorphic computing systems19
Experimental results show that the proposed fault tolerant framework can improve the successful mapping rate and simultaneously reduce the hardware cost.
- Learning Deterministic Policy with Target for Power Control in Wireless Networks19
A Deep Reinforcement Learning with Deterministic Policy and Target (DRL-DPT) framework for ICIC in wireless networks improves up to 15% of energy efficiency with faster convergence rate.
- Performance Metrics for Coverage of Cleaning Robots with MoCap System19
The first trial is made to evaluate the complete coverage path planning algorithm which is the core algorithm of a cleaning robot with Mocap system, and three simple metrics were proposed to evaluate overall performance of the algorithm.
- 19
- 19
- Optimal subband rate allocation for spatial scalability in 3D wavelet video coding with motion aligned temporal filtering19
An error propagation model is proposed to describe the effect of subband coupling in video reconstruction and the synthesis gain of each subband is estimated according to this model and it is finally adopted to guide the rate allocation algorithm.
- 18
- Object detection via deeply exploiting depth information18
This paper addresses the issue on how to more effectively coordinate the depth with RGB aiming at boosting the performance of RGB-D object detection and investigates two primary ideas under the CNN model: property derivation and property fusion.
- Integrating Answer Set Programming with Semantic Dictionaries for Robot Task Planning18
This paper proposes a novel integrated task planning system for service robots in domestic domains that exploits the knowledge on semantic roles of common verbs defined in semantic dictionaries such as FrameNet and integrates it with Answer Set Programming, a task planning framework with both representation language and solvers.
- 18
- 18
- Striatal Subdivisions Estimated via Deep Embedded Clustering With Application to Parkinson's Disease17
- 17
- 17
- Content adaptive update for lifting-based motion-compensated temporal filtering17
Simulations confirm that the proposed method improves both the rate-distortion performance for MCFT and the visual quality significantly.
- Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models16
COFT is proposed, a novelarse-to-Fine highligh\textbf{F}ine highligh\textbf{T}ing method to focus on different granularity-level key texts, thereby avoiding getting lost in lengthy contexts, leading to a superior performance over $30\% in the F1 score metric.
- 16
- 16
- 16
- Towards a Principled Solution to Simulated Robot Soccer16
A novel approach based on MAXQ-OP to automated planning in the RoboCup 2D domain that combines the benefits of a general hierarchical structure based onMAXQ value function decomposition with the power of heuristic and approximate techniques to programming autonomous agents in large stochastic domains.
- 16
- 16
- 15
- Deep Cognitive Reasoning Network for Multi-hop Question Answering over Knowledge Graphs15
A novel Deep Cognitive Reasoning Network (DCRN) is proposed, which is inspired by the dual process theory in cognitive science and significantly outperforms state-of-the-art methods on benchmark datasets.
- 15
- 15
- Free viewpoint switching in multi-view video streaming using Wyner-Ziv video coding15
A novel free viewpoint switching scheme for multi-view video scenario, in which the distributed video coding technique is employed, and the inter-camera communication can be avoided and the drifting error can be controlled efficiently when the viewpoint switching occurs.
- A heuristic multi-objective task scheduling framework for container-based clouds via actor-critic reinforcement learning14
A heuristics multi-objective task scheduling framework based on reinforcement learning (AC-CCTS) that not only solves the problems of single objective and local convergence in traditional task scheduling methods but also reduces the cost of experiential learning with reinforcement learning methods.
- An effective hybrid search algorithm for the multiple traveling repairman problem with profits14
An effective hybrid search algorithm based on the memetic algorithm framework is proposed that integrates two distinguished features: a dedicated arc-based crossover to generate high-quality offspring solutions and a fast evaluation technique to reduce the complexity of exploring the classical neighborhoods.
- 14
- Spatial Scalability in 3D Wavelet Coding with Spatial Domain MCTF Encoder14
To completely address the spatial scalability issues in spatial-domain MCTF schemes, optimization of bit allocation is needed to reasonably allocate part of the bandwidth to spatial high-frequency coefficients, instead of dropping them completely.
- 14
- Advanced NIR-II Fluorescence Imaging Technology for Precise Evaluation of Nanomedicine Delivery in Cancer Therapy13
Near-infrared II (NIR-II, 1000–1700 nm) fluorescence imaging technology serves as a non-invasive, real-time monitoring method that can be applied for the precise evaluation of nanomedicine delivery in cancer therapy due to its numerous advantages.
- DocMAE: Document Image Rectification via Self-supervised Representation Learning13
DocMAE is presented, a novel self-supervised framework for document image rectification to encode the structural cues in document images by leveraging masked autoencoder to benefit the rectification, i.e., the document boundaries, and text lines.
- 13
- 13
- 13
- Trial-Based Dynamic Programming for Multi-Agent Planning13
A novel trial-based dynamic programming algorithm for DEC-POMDPs that extends these benefits to multi-agent settings and can produce significant value improvements and is much faster than the best existing planning algorithms.
- Solving Large-Scale and Sparse-Reward DEC-POMDPs with Correlation-MDPs13
It is demonstrated that, adversarial problems can be solved by encoding the information of opponents' behavior in the correlation device and the proposed method is successfully implemented into the 2D simulated robot soccer team and the performance in RoboCup-2006 was encouraging.
- Electron Microscopy Images as Set of Fragments for Mitochondrial Segmentation12
This paper designs a coherent fragment vision transformer (FragViT) combined with affinity learning to manipulate features on 3D fragments yet explore mutual relationships to model fragment-wise context, enjoying locality prior without sacrificing global reception.
- 12
- 12
- Memristive Crossbar Mapping for Neuromorphic Computing Systems on 3D IC12
3D-FNC, a 3D floorplanning framework for neuromorphic computing systems in consideration of both crossbar utilization and design cost, and can achieve highly hardware-efficient designs, compared to state-of-the-art.
- 12
- Agile planning for real-world disaster response12
This work proposes a new model re-planning problem using a Multi-agent Markov Decision Process that integrates potential rejections as part of the planning process and proposes a novel algorithm to efficiently solve this new model.
- 12
- Compressed sensing based video multicast12
This work investigates how properties of natural images can be exploited to improve the reconstruction performance by transmitting a small amount of side information and proposes a way of exploiting inter-frame correlation by extending only the decoder.
- 12
- 11
- 11
- Receiver-driven Video Multicast over NOMA Systems in Heterogeneous Environments11
A novel receiver-driven superposed video multicast (Supcast) scheme by integrating Softcast, an analog-like transmission scheme, into the NOMA-based system to achieve high bandwidth efficiency as well as gradual decoding quality proportional to channel conditions at receivers.
- 11
- Regret-Based Multi-Agent Coordination with Uncertain Task Rewards11
This work proposes a novel decentralized algorithm that incorporates Max-Sum with iterative constraint generation to solve the problem by passing messages among agents, which scales well and can solve instances of the task allocation problem with hundreds of agents and tasks.
- 11
- IMShare11
The proposed IMShare is the first scheme to demonstrate that not only visually pleasant images can be reconstructed using this mobile-cloud method but also the reconstruction can be done in seconds using parallel computing.
- 10
- Sample-Based Policy Iteration for Constrained DEC-POMDPs10
This work proposes a novel sample-based policy iteration algorithm that improves the joint policy by solving a series of standard nonlinear programs (NLPs) thereby building on recent advances in NLP solvers and experimental results confirm the algorithm can efficiently solve constrained DEC-POMDPs that cause general DEC- POMDP algorithms to fail.
- 9
- Deeply Exploit Depth Information for Object Detection9
This paper addresses the issue on how to more effectively coordinate the depth with RGB aiming at boosting the performance of RGB-D object detection, and investigates two primary ideas under the CNN model: property derivation and property fusion.
- Social implications of agent-based planning support for human teams9
A field trial of how instructions from an intelligent planning agent are dealt with by distributed human teams, in a time-critical task setting created through a mixed-reality game is presented.
- 9
- 9
- 9
- 9
- Guiding Large Language Models in Modeling Optimization Problems via Question Partitioning8
PaMOP, a novel modeling framework based on LLMs, is proposed, to model optimization problems automatically, given only natural language descriptions, by extracting and partitioning the problems using a tree structure, guiding the LLMs to model each set of constraints with self-augmented prompts, thus reducing the demands on the LLM's capabilities of large contents.
- 8
- 8
- 8
- 8
- 8
- 8
- 7
- 7
- 7
- Posterior sampling for Monte Carlo planning under uncertainty7
This work treats the cumulative reward returned by taking an action from a search node in the MCTS search tree as a random variable following an unknown distribution and develops Dirichlet-NormalGamma based Monte Carlo tree search (DNG-MCTS) and Dirichlets based partially observable Monte Carlo planning (D2NG-POMCP) algorithms respectively for Monte Carlo plans in MDPs and POMDPs.
- 7
- 7
- 7
- 6
- 6
- 6
- 6
- Evaluation and Optimization of Kernel File Readaheads Based on Markov Decision Models6
The kernel read handling, caching and readahead behavior is formulated as an absorbing Markov decision process, and performance evaluations to compare or verify various readaheads are presented, and algorithms to find optimal prefetching policies for specific read pattern are introduced.
- Drift-free switching of compressed video bitstreams at predictive frames6
Two schemes are proposed to efficiently compress video contents into bitstreams that support drift-free switching at predictive frames and an empirical method is proposed to achieve a good tradeoff between high coding efficiency of SP frames and small size of switching bits.
- A PSO-Based Web Document Query Optimization Algorithm6
Experimental results show that the proposed PSO-based algorithm for Web document query optimization can improve the precision of document retrieval markedly compared with relevant feedback and genetic algorithm.
- 6
- Beyond Local Selection: Global Cut Selection for Enhanced Mixed-Integer Programming5
This work proposes Global Cut Selection (GCS), which uses a bipartite graph to represent the search tree and combines graph neural networks with reinforcement learning to develop cut selection strategies, and significantly improves solving efficiency for synthetic and large-scale real-world MIPs.
- Intensification-driven local search for the traveling repairman problem with profits5
An intensification-driven local search algorithm for solving the Traveling Repairman Problem with Profits by intensively investigates bounded areas around each very-high-quality local optimum encountered.
- 5
- 5
- KeJia-LC: A Low-Cost Mobile Robot Platform — Champion of Demo Challenge on Benchmarking Service Robots at RoboCup 20155
The system design and the key techniques of the mobile robot platform called KeJia-LC, who won the first place in the demo challenge on Benchmarkinng Service Robots in RoboCup 2015, are presented.
- Synthetical Benchmarking of Service Robots: A First Effort on Domestic Mobile Platforms5
The system includes a set of algorithms for collecting, recording and analyzing measurement data from a MoCap system and was used as the evaluator in a competition called the BSR challenge, in which 10 teams participated, at RoboCup 2015.
- 5
- 5
- 5
- Mode-based temporal filtering for in-band wavelet video coding with spatial scalability5
This paper introduces two new inter coding modes at macroblock level for spatial low-pass band MCTF to make a better trade-off between the lower resolution drifting error and the high resolution coding efficiency.
- A High-Fidelity Software Oscilloscope for Globus5
This work uses the MAGNET toolkit as the source of highfidelity events on each node of the grid and uses Autopilot to aggregate events from each node, to analyze application behavior and to produce data that can be conveniently displayed by other tools.
- 4
- 4
- 4
- Privacy-Preserving Policy Iteration for Decentralized POMDPs4
This work proposes the first privacy-preserving approach to address the privacy issues that arise in multi-agent planning problems modeled as a Dec-POMDP, and presents a distributed message-passing algorithm based on trials, where the agents' policies are optimized using the cross-entropy method.
- A General Batch-Calibration Framework of Service Robots4
A general batch-calibration framework is proposed, Motion Capture System is adopt as an external measurement device in virtual world so that it can provide realtime, accurate movement data of measured objects.
- 4
- 4
- Improved line-based image coding by exploiting long-distance correlations4
Line-by-line template matching (LTM) is introduced to perform the long-distance prediction of an efficient line-based image coding method (LIC) by adaptive line- by-line prediction (ALP) and adaptive residue coding.
- 4
- 4
- 4
- 4
- Structure-Aware Correspondence Learning for Relative Pose Estimation3
A novel Structure-Aware Correspondence Learning method for Relative Pose Estimation, which consists of two key modules that can naturally estimate 3D-3D correspondences for unseen objects without explicit feature matching for precise relative pose estimation.
- ClickAttention: Click Region Similarity Guided Interactive Segmentation3
This work proposes a click attention algorithm that expands the influence of positive clicks by leveraging the similarity between positively-clicked regions and the entire input, and introduces a discriminative affinity loss to reduce attention coupling between positive and negative click regions.
- 3
- 3
- Multi-Agent Planning with Baseline Regret Minimization3
A novel baseline regret minimization algorithm for multi-agent planning problems modeled as finite-horizon decentralized POMDPs that guarantees to produce a policy that is provably at least as good as a given baseline policy.
- 3
- 3
- 3
- 3
- 3
- Structured Click Control in Transformer-based Interactive Segmentation2
A structured click intent model based on graph neural networks, which adaptively obtains graph nodes via the global similarity of user-clicked Transformer tokens, and will be aggregated to obtain structured interaction features to enhance the control of clicks over segmentation results.
- Test-Time Adaptation via Style and Structure Guidance for Histological Image Registration2
This paper proposes a novel test-time adaptation method for histological image registration, aiming to improve the generalization ability of learning-based methods, and introduces a smoothing strategy to leverage historical models for better generalization.
- Test-Time Training for Deep MS/MS Spectrum Prediction Improves Peptide Identification2
PepT3 is developed, a test-time training paradigm that adapts the pretrained model to generate experimental data-specific models, namely, PepT3, that yields a 10-40% increase in peptide identification depending on the variability in training and experimental data.
- 2
- An Extended Correlation Dimension of Complex Networks2
The correlation dimension is extended to the weighted networks and used to analyze the fractal properties of the Newman–Watts (NW) unweighted small-world networks.
- 2
- Multimedia Immersive Technologies and Networking2
This course aims to improve the quality of research in the area of computer science and electronic engineering in China by providing real-time information about machine learning techniques and user interfaces.
- Flexible p-picture (FLEXP) coding for tue efficient fine-granular scalabilitv (FGS)2
The proposed FlexP technique provides more flexibility on bandwidth adaptation, as well as achieves a good trade-off between high coding efficiency and low drifting error at the enhancement layer especially when the R-D rate allocation is enabled.
- 1
- 1
- Human-UAV Teaming in Dynamic and Uncertain Environments1
In this demonstrator, an algorithm developed for human-agent coordination can be used to coordinate human actors on the ground and unmanned aerial vehicles in a rescue mission.
- 1
- 1
- Scalable Wyner-Ziv video coding with adaptive bit-plane representation1
A simplified adaptive bit-plane representation is proposed without pre-knowing the Laplacian distribution parameters for the DCT-domain Wyner-Ziv video coding, in which the encoding can stop at any bit-planes and the bit-stream can also be flexibly truncated.
- Quality-fluctuation-constrained rate allocation for MCTF-based video coding1
This paper presents a new rate allocation algorithm for MCTF-based video coding with the aim to control quality fluctuation and verifies it on MPEG SVC reference software and demonstrates that the proposed rate allocation scheme can reduce quality fluctuations significantly.
- Bitstream switching for progressive fine granularity scalable video coding1
Compared with other bitstream switching schemes, the proposed scheme shows its flexibilities and various advantages due to using the common base layer, and can significantly improve the streaming performance of the scalable bitstreams.
- –
- Scalable Mixed-Integer Optimization with Neural Constraints via Dual Decomposition–
A novel dual-decomposition framework is introduced that relaxes the single coupling equality u=x with an augmented Lagrange multiplier and splits the problem into a vanilla MIP and a constrained NN block, which proves scalable, modular, and adaptable.
- –
- –
- –
- –
- –
- –
- –
- Multi-agent Planning with High-Level Human Guidance–
This work proposes an extension of decentralized POMDPs that allows a human operator who observes a multi-agent team to provide valuable guidance to the team based on her superior ability to interpret observations and assess the overall situation and can lead to dramatic improvement in performance.
- –
- –
- –
- Stochastic multi-agent planning with partial state models–
An algorithm for computing policies based on history samples that include human labeled data in the form of reward reshaping is presented, offering the first approach to incorporating human knowledge in such complex multi-agent settings.
- –
- A Robust Algorithm: Find an Unknown Person via Referring Grounding–
A probabilistic model is used to ground the target person and the acceptability of color descriptions is modeled based on visual similarity and the confusion matrix of the color classifier which make the system more robust to illumination.
- A Composable Workflow for Productive FPGA Computing via Whole-Program Analysis and Transformation (with Code Excerpts)–
A composable workflow to enable highly-productive heterogeneous computing on FPGAs by providing complementary tools for automatic CUDA-to-OpenCL translation and compile-time OpenCL validation in advance of very expensive compilation, placement, and routing on FGPAs.
- –
- –
- –
- –
- –
- Guest Editorial Special Issue on Advances in Multimedia Computing, Communications and Applications–
Ten papers published in this special issue cover a wide range of techniques and applications in various multimedia processing tasks, including multimedia analysis and retrieval, compression and optimization, communication and networking, and multimedia system and applications.
- –
- –
- Distributed Video Coding with Trellis Coded Quantization–
Experimental results indicate that though the simplest TCQ is used, gain is also achieved over scalar quantization, and a method to solve the refinement problem is proposed.
- A Cross-Resolution Leaky Prediction Scheme for In-Band Wavelet Video Coding with Spatial Scalability–
- –
- Design and Implementation of the General Query Module with VJ–
This paper designs and develops such a general query module with VJ++, which has the characteristics of good independence, powerful generality and friendly interface support.
- A Timed Petri Net Model and Optimal Control of Chemical Batch Process–
This paper uses both timed Petri net and dynamic programming for modeling and optimizingchemical batch process in accordance with their special characteristics and optimization problems.
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.