Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Wan-Chi SiuSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works291 from public data
- Hexagon-based search pattern for fast block motion estimation897
Analysis shows that a speed improvement rate of the hexagon-based search (HEXBS) algorithm over the diamond search (DS) algorithm can be over 80% for locating some motion vectors in certain scenarios.
- Low-Light Image Enhancement with Normalizing Flow650
This paper investigates to model this one-to-many relationship via a proposed normalizing flow model of an invertible network that takes the low-light images/features as the condition and learns to map the distribution of normally exposed images into a Gaussian distribution.
- SinSR: Diffusion-Based Image Super-Resolution in a Single Step378
This work first derive a deterministic sampling process from the most recent state-of-the-art (SOTA) method for accelerating diffusion-based SR, which can be distilled into a student model that performs SR within only one inference step, resulting in a remarkable up to × 10 speedup for inference.
- 259
- 227
- Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework204
A novel derain algorithm is proposed, which applies superpixel (SP) segmentation to decompose the scene into depth consistent units and shows that much cleaner rain removal is achieved especially for highly dynamic scenes with heavy and opaque rainfall from a fast moving camera.
- 201
- 176
- 135
- 113
- Light Field Compression With Disparity-Guided Sparse Coding Based on Structural Key Views106
An LF codec with disparity guided Sparse Coding over a learned perspective-shifted LF dictionary based on selected Structural Key Views (SC-SKV), which produces convincing compression results in terms of both rate-distortion performance and visual quality compared with Joint Exploration Model.
- Fast approach for H.264 inter mode decision101
Experimental results show that the proposed method can efficiently save the computation cost for inter mode decision while maintaining the same PSNR and bit rate.
- Rethinking and Designing a High-Performing Automatic License Plate Recognition Approach99
The proposed VSNet outperforms state-of-the-art methods by more than 50% relative improvement on error rate, achieving >99% recognition accuracy on CCPD and AOLP datasets with 149 FPS inference speed and illustrates an outstanding generalization capability when evaluated on the unseen PKUData and CLPD datasets.
- 98
- 92
- ExposureDiffusion: Learning to Expose for Low-light Image Enhancement90
This work seamlessly integrating a diffusion model with a physics-based exposure model to achieve significantly improved performance and reduced inference time and proposes an adaptive residual layer that effectively screens out the side-effect in the iterative refinement when the intermediate results have been already well-exposed.
- A soft MAP framework for blind super-resolution image reconstruction87
A new soft maximum a posteriori (MAP) estimation framework to perform joint blur identification and HR image reconstruction that incorporates a soft blur prior that estimates the relevance of the best-fit parametric blur model, and induces reinforcement learning towards it.
- A survey on occupancy perception for autonomous driving: The information fusion perspective84
This survey reviews the most recent works on 3D occupancy perception, and provides in-depth analyses of methodologies with various input modalities, and evaluates and analyze the occupancy perception performance of the state-of-the-art on the most popular datasets.
- 82
- 78
- 78
- TAFNet: A Three-Stream Adaptive Fusion Network for RGB-T Crowd Counting73
A three-stream adaptive fusion network named TAFNet, which uses paired RGB and thermal images for crowd counting, which achieves more than 20% improvement on mean average error and root mean squared error compared with state-of-the-art method.
- 72
- 66
- A motion vector recovery algorithm for digital video using lagrange interpolation64
This paper proposes an efficient motion vector recovery algorithm for the new coding standard H.264, which makes use of the Lagrange interpolation formula, and shows that the algorithm can efficiently improve the visual quality of corrupted video.
- A Survey of Embodied Learning for Object-centric Robotic Manipulation63
A comprehensive survey of the latest advancements in embodied learning for object-centric robotic manipulation and categorize the existing work into three main branches: 1) Embodied perceptual learning, which aims to predict object pose and affordance through various data representations.
- Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restoration61
An Attention-guided Progressive Neural Texture Fusion (APNT-Fusion) HDR restoration model which aims to address issues over content association ambiguities caused by saturation, motion, and various artifacts introduced during multi-exposure fusion such as ghosting, noise, and blur is proposed.
- Light Field Denoising via Anisotropic Parallax Analysis in a CNN Framework58
Extensive experiments show that the proposed APA LF denoiser provides a much better denoising performance than state-of-the-art methods in terms of visual quality and in preservation of parallax details.
- Recursive algorithm for the discrete cosine transformwith general lengths57
A novel VLSI algorithm for computing the discrete cosine transform of variable length by using some mathematical techniques, which is particularly suitable for the real-time computation of the DCT and can be implemented using regular and parallel V LSI structures, so that the computational complexity is greatly reduced.
- Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation55
This paper proposes a simple, effective, and plug-and-play training strategy named Knowledge Distillation for Domain Generalization (KDDG) which is built upon a knowledge distillation framework with the gradient filter as a novel regularization term that can significantly improve the generalization capability of deep neural networks.
- Simultaneous Spatial and Spectral Low-Rank Representation of Hyperspectral Images for Classification53
- 48
- 44
- 42
- An Efficient Arbitrary Downsizing Algorithm for Video Transcoding42
This arbitrary downsizing algorithm is processed directly in the discrete cosine transform domain and is not only applicable to an intracoding frame but also to an intercoding frame.
- 40
- Convolutional Neural Networks With Dynamic Regularization39
This article proposes a dynamic regularization method for CNNs that can dynamically adjust the regularization strength in the training procedure, thereby balancing the underfitting and overfitting of CNNs.
- 39
- 39
- 38
- Human Motion Capture Data Tailored Transform Coding37
This paper proposes a novel mocap-tailored transform coding algorithm that significantly outperforms state-of-the-art algorithms in terms of compression performance and speed.
- 37
- 37
- 37
- A fast octagon-based search algorithm for motion estimation36
A novel algorithm using octagon-based search (OCTBS) pattern for fast block motion estimation that can find a motion vector with fewer search points than the diamond search (DS) algorithm is proposed.
- Human motion capture data recovery using trajectory‐based matrix completion35
Experiments show that the proposed motion capture data recovery method performs significantly better for nearly all tested motion sequences and amounts of missing data.
- 34
- Dense Point Prediction: A Simple Baseline for Crowd Counting and Localization33
A localization head is proposed to distinguish dense crowds trained by two loss functions, i.e., Negative-Suppressed Focal (NSF) loss and False-Positive (FP) loss, which balances the positive/negative examples and handles the false-positive predictions.
- 32
- Efficient implementation of discrete cosine transform using recursive filter structure32
A formulation for converting a length-2/sup n/ discrete cosine transform into n groups of equations is generalized and converted into recursive filter form, which is particularly simple for practical implementation.
- Weakly-Supervised Part-Attention and Mentored Networks for Vehicle Re-Identification31
This paper proposes a weakly-supervised Part-Attention Network (PANet) and Part-Mentored Network (PMNet) for Vehicle Re-ID and adopts Homoscedastic Uncertainty to learn the optimal weighing of ID losses.
- 31
- Raw Image Reconstruction with Learned Compact Metadata29
A novel framework to learn a compact representation in the latent space serving as the metadata in an end-to-end manner with the improved entropy estimation strategies, which leads to better reconstruction quality, smaller size of metadata, and faster speed.
- Deep Spatial-Angular Regularization for Compressive Light Field Reconstruction over Coded Apertures29
A novel learning-based framework for the reconstruction of high-quality LFs from acquisitions via learned coded apertures that incorporates the measurement observation into the deep learning framework elegantly to avoid relying entirely on data-driven priors for LF reconstruction.
- 28
- 27
- Fall detection based on skeleton extraction26
Experimental results show that with the help of correction the proposed fall detection method could outperform the existing RDF based method.
- PEM: Perception Error Model for Virtual Testing of Autonomous Vehicles25
This article defines Perception Error Models (PEM), a virtual simulation component that can enable the analysis of the impact of perception errors on AV safety, without the need to model the sensors themselves.
- 25
- 25
- 25
- 24
- 23
- Smooth constrained motion estimation for video coding23
Simulation results show that by applying the new criterion in motion estimation, both the improvement in peak signal-to-noise ratio (PSNR) and the reduction in bit rate up to 4.3% can be achieved compared to MAD.
- 23
- 22
- 22
- 21
- 21
- Motion capture data recovery using skeleton constrained singular value thresholding21
This work extends the SVT method for mocap recovery to include skeleton constraints, utilizing the fact that human bones are rigid to constrain inter-marker distances of specific sets of markers.
- 21
- 21
- 21
- 20
- NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Methods and Results19
The NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration provides a common benchmark for evaluating restoration methods under realistic corruption settings and provides useful insights for future research on robust video restoration under practical bitstream corruption.
- SGIFormer: Semantic-Guided and Geometric-Enhanced Interleaving Transformer for 3D Instance Segmentation19
This paper introduces a novel method, named SGIFormer, for 3D instance segmentation, which is composed of the Semantic-guided Mix Query (SMQ) initialization and the Geometric-enhanced Interleaving Transformer (GIT) decoder.
- 19
- 19
- An error-resilient GOP structure for robust video transmission19
By selecting the optimal position of the I frame in a GOP, robustness can be achieved without reducing any coding efficiency, and it provides reverse-play operation for MPEG video streaming with much less requirement on the network bandwidth.
- 19
- SignEye: Traffic Sign Interpretation From Vehicle First-Person View18
A traffic guidance assistant (TGA) scenario application is developed to re-explore the role of traffic signs in ADS as a complement to popular autonomous technologies (such as obstacle perception) and results demonstrate that the TGA can provide complementary information to ADS beyond existing popular autonomous technologies.
- 18
- 18
- 18
- 17
- 17
- 17
- Direct formulation for the realization of discrete cosine transform using recursive structure17
This paper suggests using some suitable mappings to convert a prime length DCT into two suitable transforms with approximately half of the original length to effect fast realization.
- A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarking15
This study conducted meticulous experiments with numerous different classifiers and detectors, encompassing a wide range of mainstream methods, and uncovered insightful and intriguing findings, which shed light on the relationship between adversarial noise crafting and model training.
- Bitstream-Corrupted JPEG Images are Restorable: Two-stage Compensation and Alignment Framework for Image Restoration15
A robust JPEG decoder is proposed, followed by a two-stage compensation and alignment framework to restore bitstream-corrupted JPEC images, and experimental results and ablation studies demonstrate the superiority of the proposed method.
- 15
- 14
- 14
- 14
- HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis13
HVG-3D, a unified framework for 3D-aware hand-object interaction (HOI) video synthesis conditioned on explicit 3D representations, is proposed, which develops a diffusion-based architecture augmented with a 3D ControlNet, which encodes geometric and motion cues from 3D inputs to enable explicit 3D reasoning during video synthesis.
- A Byte Sequence is Worth an Image: CNN for File Fragment Classification Using Bit Shift and n-Gram Embeddings13
This work proposes Byte2Image, a novel data augmentation technique, to introduce the neglected intra-byte information into file fragments and re-treat them as 2d gray-scale images, which allows us to capture both inter-byte and intra- byte correlations simultaneously through powerful convolutional neural networks (CNNs).
- Moving Towards Centers: Re-Ranking With Attention and Memory for Re-Identification13
This paper proposes a re-ranking network to predict the correlations between the probe and top-ranked neighbor samples, which surpasses the state-of-the-art re- ranking approaches on large-scale datasets by a significant margin.
- 13
- Low-latency compression of mocap data using learned spatial decorrelation transform13
Two efficient methods to compress mocap data with low latency by learning an orthogonal transform to reduce the spatial redundancy and adopting a predictive coding and temporal DCT for temporal decorrelation in the frame- and clip-oriented methods.
- 13
- 13
- Beyond Learned Metadata-Based Raw Image Reconstruction12
A novel framework that learns a compact representation in the latent space, serving as metadata, in an end-to-end manner is proposed, achieving high-quality raw image reconstruction with a smaller metadata size, compared with existing SOTA methods.
- 12
- 12
- 12
- REAL: Representation enhanced analytic learning for exemplar-free class-incremental learning11
A representation-enhanced analytic learning (REAL) is proposed, which achieves state-of-the-art performance on CIFAR-100, ImageNet-100 and ImageNet-1k benchmarks, outperforming exemplar-free methods and rivaling exemplar-based approaches.
- CaRe-Ego: Contact-aware relationship modeling for egocentric interactive hand-object segmentation11
A novel method called CaRe-Ego is proposed that achieves state-of-the-art performance by emphasizing the contact between hands and objects from two aspects and significantly outperforms existing methods with robust generalization capability.
- 11
- Remote detection of idling cars using infrared imaging and deep networks11
The first automatic system to detect idling cars, using infrared (IR) imaging and deep networks, is proposed, based on the differences in spatio-temporal heat signatures of idling and stopped cars and monitor the car temperature with a long-wavelength IR camera.
- 11
- 11
- 11
- 11
- 11
- 11
- 11
- 11
- PromptSR: Cascade Prompting for Lightweight Image Super-Resolution10
The experimental results demonstrate the superiority of the PromptSR method, which outperforms state-of-the-art lightweight SR methods in quantitative, qualitative, and complexity evaluations.
- 10
- 10
- 10
- 10
- 10
- 10
- ANNEXE: Unified Analyzing, Answering, and Pixel Grounding for Egocentric Interaction9
A unified ANNEXE model is designed to generate text- and pixel-level outputs utilizing multimodal large language models, which enables a comprehensive interpretation of egocentric interactions.
- 9
- Streaming 3D meshes using spectral geometry images9
It is shown that SGI is more effective than GI to generate visually pleasing shapes at high compression rates and by coupling SGI to the proposed error protection scheme, it is able to ensure the smooth delivery of 3D model across error networks for different packet loss rate simulated using the two-state Markov model.
- 9
- 8
- CoPEM: Cooperative Perception Error Models for Autonomous Driving8
The notion of Cooperative Perception Error Models (coPEMs) is introduced towards achieving an effective and efficient integration of V2X solutions within a virtual test environment and the safety achievable by an AV challenged with a traffic scenario where occlusion is the primary cause of a potential collision is compared.
- 8
- Deepsea video descattering8
This paper robustly approximate the deepsea video to recover its background using online robust principal component analysis in a sub-video-by-sub-video manner and extracts structure information from the approximation error to compensate the obtained background, which is formulated as a constrained convex optimization problem.
- 8
- Efficient recursive algorithm for the inverse discrete cosine transform8
By using some appropriate iterative techniques, the formulation of the IDCT can be implemented effectively using recursive equations, and the hardware complexity is further reduced as compared with the approaches in the literature.
- 7
- Multi-Object Tracking with Tracked Object Bounding Box Association7
This paper proposes to incorporate a simple tracked object bounding box and overlapping prediction based on the current frame onto the CenterTrack algorithm and proposes an Intersection over Union (IOU) distance cost matrix in the association step instead of simple point displacement distance.
- 7
- 7
- 7
- 7
- Efficient multiplier structure for realization of the discrete cosine transform7
This paper represents the cosine coefficient in binary form and realize multiplications using a new serial–parallel multiplier architecture that results in a simple structure for VLSI realization.
- Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges6
This paper identifies three core tasks in EgoProceAssist: egocentric procedural error detection, egocentric procedural learning, and egocentric procedural question answering, and introduces two enabling dimensions: real-time and streaming video understanding, and proactive interaction in procedural contexts.
- Towards Blind Bitstream-corrupted Video Recovery: A Visual Foundation Model-driven Framework6
This paper proposes the first blind bitstream-corrupted video recovery framework that integrates visual foundation models with recovery model, which is adapted to different types of corruption and bitstream-level prompts and introduces a novel Corruption-aware Feature Completion (CFC) module.
- 6
- 6
- 6
- Human Computer Interface for Quadriplegic People Based on Face Position/gesture Detection6
The experimental results show that the proposed interface is comfortable, easy to use, robust, and outperforms the existing assistive technology.
- Dynamic 3-D facial compression using low rank and sparse decomposition6
Taking advantage of the near-isometric property of human facial expressions, dynamic 3-D faces are parameterize into an expression-invariant canonical domain, which naturally generates geometry video and allows us to apply the well-studied video compression technique.
- 6
- 6
- 6
- Dynamic frame-skipping transcoding with motion information considered6
Experimental results show that the proposed method can present a smooth frame rate variation, and well preserve the original motion information with tolerable delay, and spatial quality is also improved.
- 6
- Interaction-aware Representation Modeling with Co-occurrence Consistency for Egocentric Hand-Object Parsing5
This work proposes an end-to-end Interaction-aware Transformer (InterFormer), which integrates three key components, i.e., a Dynamic Query Generator, a Dual-context Feature Selector (DFS), and the Conditional Co-occurrence (CoCo) loss, and achieves state-of-the-art performance on both the EgoHOS and the challenging out-of-distribution mini-HOI4D datasets.
- 5
- 3DGeoDet: General-Purpose Geometry-Aware Image-Based 3D Object Detection5
The predicted depth is utilized to learn voxel occupancy and optimize the voxelized 3D feature volume explicitly through the proposed voxel occupancy attention, and an implicit 3D representation is integrated with an implicit 3D representation, the truncated signed distance function (TSDF).
- 5
- Removing Image Artifacts From Scratched Lens Protectors5
This work considers the inherent challenges in a unified framework with two cooperative modules, which facilitate the performance boost of each other, and demonstrates that the method outperforms the baselines qualitatively and quantitatively.
- 5
- 5
- 5
- 5
- 5
- 5
- Efficient inner search for faster diamond search5
Enhanced DS incorporating the proposed fast inner search can achieve a significant speedup gain while maintaining similar or smaller distortion, which is clearly demonstrated in the extensive experiments on 10 video sequences.
- 5
- LaSSM: Efficient Semantic-Spatial Query Decoding via Local Aggregation and State Space Models for 3D Instance Segmentation4
LaSSM is introduced, a hierarchical semantic-spatial query initializer to derive the query set from superpoints by considering both semantic cues and spatial distribution, achieving comprehensive scene coverage and accelerated convergence.
- Revealing the intrinsic ethical vulnerability of aligned large language models4
It is proved current alignment creates only local safety regions, leaving global adversarial paths intact, and empirically show widespread vulnerability across leading aligned models, showing a fundamental structural weakness in current aligned LLMs.
- EDVD-LLaMA: Explainable Deepfake Video Detection via Multimodal Large Language Model Reasoning4
This paper proposes the explainable deepfake video detection (EDVD) task and designs the EDVD-LLaMA multimodal, a large language model (MLLM) reasoning framework, which provides traceable reasoning processes alongside accurate detection results and trustworthy explanations.
- GaussianCross: Cross-modal Self-supervised 3D Representation Learning via Gaussian Splatting4
GaussianCross is presented, a novel cross-modal self-supervised 3D representation learning architecture integrating feed-forward 3D Gaussian Splatting techniques to address current challenges and shows a prominent parameter and data efficiency.
- Attack Anything: Blind DNNs via Universal Background Adversarial Attack4
The findings of this research substantiate the significant discrepancy between human and machine vision on the value of background variations, which play a far more critical role than previously recognized, necessitating a reevaluation of the robustness and reliability of DNNs.
- 4
- 4
- 4
- 4
- 4
- 4
- A New Rate-Quantization Model for H.264/AVC Low-Delay Rate Control4
A new rate-quantization (R-Q) model for H.264/AVC low-delay rate control is presented, which has shown that almost 2x performance improvement in terms of the bits mismatch error.
- 4
- Synchronized partial-body motion graphs4
An automatic method to construct a new data structure that specifies transitions and correlations between partial-body motions, called Synchronized Partial-body Motion Graphs (SPbMGs), that maximizes the reusability of motion data, but also increases the connectivity of motion graphs while retaining the quality of motion.
- 4
- 4
- 4
- 4
- 4
- EVA02-AT: Egocentric Video-Language Understanding With Spatial-Temporal Rotary Positional Embeddings and Symmetric Optimization3
This paper introduces EVA02-AT, a suite of EVA02-based video-language foundation models tailored to egocentric video understanding tasks, and introduces the Symmetric Multi-Similarity (SMS) loss and a novel training framework that advances all soft labels for both positive and negative pairs, providing a more precise learning objective.
- PADetBench: Towards Benchmarking Physical Attacks against Object Detection3
Realistic simulation is explored utilizing realistic simulation to thoroughly and rigorously benchmark physical attacks with fairness under controlled physical dynamics and cross-domain transformation, resolving the problem of capturing identical adversarial images that cannot be achieved in the real world.
- 3
- Portrait matting using an attention-based memory network3
The attention-based memory block is designed by combining the idea of the memory network and self-attention to compute pixel-level temporal coherence among video frames to enhance the overall performance.
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- EgoProceVQA: A Novel Egocentric Procedural Understanding Task with Self-Skill-Exploration Agent2
The Egocentric Procedural Understanding VQA task is introduced, which systematically evaluates egocentric procedural reasoning abilities of current MLLMs and agents through six types of key-step-centric questions, and EgoProceAgent, a self-skill-exploration agentic framework, a generic tool library for procedural understanding and a standardized sub-skill library shared across tools and models are designed.
- Future-Proofing Deepfake Detection by Integrating Audio, Video, and Text2
This perspective letter advocates for a new paradigm in deepfake detection that emphasizes the integration of audio, video, and textual content, and examines the limitations of current systems, including their over-reliance on outdated datasets and limited adversarial robustness.
- HAMMER: Harnessing MLLM via Cross-Modal Integration for Intention-Driven 3D Affordance Grounding2
This work proposes a novel framework that leverages emerging multimodal large language models (MLLMs) for interaction intention-driven 3D affordance grounding, namely HAMMER, and devise a hierarchical cross-modal integration mechanism to fully exploit the complementary information from the MLLM for 3D representation refinement.
- Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep2
HetCache is introduced, a training-free diffusion acceleration framework designed to exploit the inherent heterogeneity in diffusion-based masked video-to-video (MV2V) generation and editing, which reduces redundant attention operations while maintaining editing consistency and fidelity.
- 2
- Symmetric Multi-Similarity Loss for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 20242
This report proposes a novel loss function, Symmetric Multi-Similarity Loss, which offers a more precise learning objective and achieves 63.76% average mAP and 74.25% average nDCG on the public leaderboard, demonstrating the effectiveness of the approach.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- Concurrent computation of two-dimensional discrete cosine transform2
A novel VLSI algorithm for the computation of a two-dimensional discrete cosine transform that has temporal and spatial locality of connection and can be segmentized for pipeline operations, so the computation time is greatly reduced.
- ProCal: Probability Calibration for Neighborhood-Guided Source-Free Domain Adaptation1
ProCal, a probability calibration method that dynamically calibrates neighborhood-based predictions through a dual-model collaborative prediction mechanism, is introduced, achieving a balance between knowledge retention and domain adaptation.
- EARL: Towards a Unified Analysis-Guided Reinforcement Learning Framework for Egocentric Interaction Reasoning and Pixel Grounding1
EARL is an Egocentric Analysis-guided Reinforcement Learning framework that explicitly transfers coarse interaction semantics to query-oriented answering and grounding, and adopts a two-stage parsing framework including coarse-grained interpretation and fine-grained response.
- GUI-C$^2$: Coarse-to-Fine GUI Grounding via Difficulty-Aware Reinforcement Learning1
This work proposes GUI-D, a data mining and difficulty scoring pipeline that identifies the training-worthy samples by proper testing and assigns difficulty scores to guide subsequent training weights, and employs an area-gated coarse-to-fine refinement mechanism that progressively narrows the visual field via model-internal uncertainty signals.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Lattice-Support repetitive local feature detection for visual search1
Experiments performed on benchmark datasets show that the proposed LS-RLF detection method outperforms the state-of-the-art methods by mean Average Precisions (mAP) of 4.5%, 5.5% and 3.2% on Oxford, Paris, and INRIA holidays datasets respectively.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Adaptive resynchronization approach for scalable video over wireless channel1
It is shown from experimental results that the proposed adaptive resynchronization method can perform a graceful degradation under a variety of error conditions and shows advantages over conventional method.
- 1
- 1
- 1
- 1
- 1
- 1
- Content-Based Resynchronization for Robust Video Transmission1
Using macroblock (MB)-based segmentation results, a framework for the positioning of resynchronization markers such that the image quality of foreground can be improved at the expense of sacrificing the unimportant background is proposed.
- 1
- Efficient prime factor algorithm and address generation techniques for the discrete cosine transform1
By using the proposed mappings and address generation techniques, less temporary storage is required, such that a reduction of memory requirement can be achieved during the implementation of the prime factor algorithm for the discrete cosine transform.
- Transform domain recursive algorithm to compute discrete cosine and sine transforms1
A new realization scheme using the recursive property of the transform domain to compute the DCT and the DST sequentially sequentially and the output efficiency is improved and the total processing time is reduced.
- –
- –
- –
- –
- –
- Evolution-Inspired Sample Competition for Deep Neural Network Optimization–
Natural Selection (NS) is presented, a novel evolution-inspired optimization method that explicitly incorporates competitive interactions into deep network training and enables more adaptive and balanced model optimization.
- SP-MoMamba: Superpixel-driven Mixture of State Space Experts for Efficient Image Super-Resolution–
The proposed Superpixel-driven State Space Model (SP-SSM) organizes spatially coherent features into compact region-level tokens and performs global sequence modeling over these content-aware representations, reducing redundant computation while facilitating long-range structural interaction.
- MASS: Mesh-inellipse Aligned Deformable Surfel Splatting for Hand Reconstruction and Rendering from Egocentric Monocular Video–
This work introduces the mesh-aligned Steiner Inellipse and fractal densification for mesh-to-surfel conversion that initiates high-resolution 2D Gaussian surfels from coarse parametric hand meshes, providing surface representation with photorealistic rendering potential.
- –
- Blind object detectors via transferable background adversarial attack–
The findings of this research substantiate the significant discrepancy between human and machine vision on the value of background variations, which play a far more critical role than previously recognized, necessitating a reevaluation of the robustness and reliability of DNNs.
- –
- Probabilistic Mixture of Hyperbolic Mamba for Few-Shot Class-Incremental Learning–
This paper presents a novel framework named Probabilistic Mixture of Hyperbolic State Space Experts (PmH-SSE), and proposes the probabilistic mixture of Mamba to increase the model's flexibility in handling non-stationary data streams in FSCIL and enhance the stability of high-parameter models in few-shot conditions.
- –
- HSNet: Heterogeneous Subgraph Network for Single Image Super-resolution–
The Heterogeneous Subgraph Network (HSNet) is proposed, a novel framework that efficiently leverages graph modeling while maintaining computational feasibility, and achieves state-of-the-art performance, effectively balancing reconstruction quality with computational efficiency.
- F-OAL: Forward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental Learning–
Instead of back-propagation, the Analytic Classifier (AC) updated by recursive least square, cooperating with a frozen backbone is designed, which simultaneously achieves high accuracy, low resource consumption and data privacy protection.
- –
- –
- –
- –
- Human Motion Capture Data Compression based on Learned Spatial Transform.–
This paper proposes a very effective transform, namely learned orthogonal transform (LOT), for reducing the spatial redundancy in human mocap data and adopts a predictive coding and temporal DCT for temporal decorrelation in the frame- and clip-based frameworks.
- –
- –
- Single Viewpoint Image-Driven Simplification–
The proposed single viewpoint simplification runs at least 25 times faster than the previous approach with better quality overall and formulating a new error metric is devised.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Efficient Recursive Algorithm for the Inverse Discrete–
An efficient recursive algorithm for the inverse discrete cosine transform with arbitrary length is presented and the hardware complexity is further reduced as compared with the approaches in the literature.
- –
- –
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.