Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks96 from public data
- Cross-Modality Person Re-Identification With Shared-Specific Feature Transfer418
This paper proposes a novel cross-modality shared-specific feature transfer algorithm (termed cm-SSFT) to explore the potential of both the modality-shared information and themodality-specific characteristics to boost the reidentification performance.
- Online Multi-object Tracking Using CNN-Based Single Object Tracker with Spatial-Temporal Attention Mechanism391
A CNN-based framework for online MOT that utilizes the merits of single object trackers in adapting appearance models and searching for target in the next frame and introduces spatial-temporal attention mechanism (STAM) to handle the drift caused by occlusion and interaction among targets.
- Geometry Uncertainty Projection Network for Monocular 3D Object Detection316
A GUP Net is proposed to tackle the error amplification problem at both inference and training stages and can infer more reliable object depth than existing methods and outperforms the state-of-the-art image-based monocular 3D detectors.
- MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small-Target Detection227
Inspired by the recent basic model with linear complexity for long-distance modeling, Mamba, the potential of this state-space model (SSM) for ISTD tasks in terms of effectiveness and efficiency is explored.
- 170
- 133
- GSM: Graph Similarity Model for Multi-Object Tracking130
This paper proposes a novel graph representation that takes both the feature of individual object and the relations among objects into consideration and, with the help of the graph representation and the graph matching module, the proposed graph similarity model is more robust to the occlusion and the targets sharing similar appearance.
- Temporal ROI Align for Video Object Recognition125
A novel Temporal ROI Align operator is proposed to extract features from other frames feature maps for current frame proposals by utilizing feature similarity, and can extract temporal information from the entire video for proposals.
- Efficient Semantic Image Synthesis via Class-Adaptive Normalization114
A truly spatially-adaptive variant of CLADE, namely CLADE-ICPE, which can be generalized to different SPADE-based methods while achieving comparable generation quality compared to SPADE, but it is much more efficient with fewer extra parameters and lower computational cost.
- Online multi-object tracking with unsupervised re-identification learning and occlusion estimation111
This study shows that, when applied to state-of-the-art MOT methods, the proposed unsupervised re-Identification learning is comparable to supervised re-identification learning, and the tracking performance is further improved by the proposed occlusion estimation module.
- 110
- Reduce Information Loss in Transformers for Pluralistic Image Inpainting104
A patch-based auto-encoder P-VQVAE, where the encoder converts the masked image into non-overlapped patch tokens and the decoder recovers the masked regions from the inpainted tokens while keeping the unmasked regions unchanged is designed.
- Joint Color-irrelevant Consistency Learning and Identity-aware Modality Adaptation for Visible-infrared Cross Modality Person Re-identification98
This work proposes a novel approach to VI-ReID that learns the color-irrelevant features through the CICL and aligns the identity-level feature distributions by the Identity-aware modality adaptation (IAMA), which is integrated into a joint learning framework and can promote each other.
- Mining Contextual Information Beyond Image for Semantic Segmentation98
This paper proposes to mine the contextual information beyond individual images to further augment the pixel representations and proposes a representation consistent learning strategy to make the classification head better address intra-class compactness and inter-class dispersion.
- 94
- Diverse Semantic Image Synthesis via Probability Distribution Modeling81
This paper proposes a novel diverse semantic image synthesis framework from the perspective of semantic class distributions, which naturally supports diverse generation at semantic or even instance level by modeling class-level conditional modulation parameters as continuous probability distributions instead of discrete values.
- 76
- MichiGAN73
MichiGAN (Multi-Input-Conditioned Hair Image GAN), a novel conditional image generation method for interactive portrait hair manipulation that allows fully-conditioned hair generation from multiple user inputs, is presented.
- 50
- 50
- 49
- Three-dimensional reconstruction using an adaptive simultaneous algebraic reconstruction technique in electron tomography47
Experimental results show that the proposed technique ASART is better based on objective quality measures than other methods, especially when data is noisy and limited in tilt angles, and outperforms that of simultaneous algebraic reconstruction technique (SART) in speed.
- 44
- 40
- DASOT: A Unified Framework Integrating Data Association and Single Object Tracking for Online Multi-Object Tracking38
An efficient two-stage tracking method in the SOT branch, which utilizes the merits of correlation features and can simultaneously track all the existing targets within one forward propagation, is proposed.
- Using multi-label classification to improve object detection36
A novel multi-task framework for object detection that uses multi-label classification as an auxiliary task to improve object detection, and can be trained and tested end-to-end and does not require any extra annotation.
- Transformer Based Pluralistic Image Completion With Reduced Information Loss35
A patch-based auto-encoder that directly takes features from the P-VQVAE encoder as input without any quantization and only regards the quantized tokens as prediction targets is designed, which greatly outperforms existing transformer based methods on image fidelity.
- Exploring the Application of Large-Scale Pre-Trained Models on Adverse Weather Removal35
This paper designs a Spatially Adaptive Residual (SAR) encoder to adaptively extract degraded areas and proposes a CLIP Weather Prior (CWP) embedding module to enable the network to adaptively respond to different weather conditions.
- Density-Aware Graph for Deep Semi-Supervised Visual Recognition34
This paper proposes a new Density-aware Neighborhood Aggregation module to learn more discriminative features by incorporating the neighborhood information in a density-aware manner and a novel D density-ascending Path based Label Propagation module to generate the pseudo-labels for unlabeled samples more efficiently according to the feature distribution characterized by density.
- 34
- 32
- 30
- 30
- MFMS: Learning Modality-Fused and Modality-Specific Features for Deepfake Detection and Localization Tasks29
The proposed solution to the AV-Deepfake1M competition, which provides a large-scale dataset named AV-Deepfake1M to boost the research in this area, and the solutions which have achieved top performance in this competition are presented.
- 27
- Towards Generalizable and Robust Face Manipulation Detection via Bag-of-feature26
This paper extends Transformers using bag-of-feature approach to encode inter-patch relation-ships, allowing it to learn forgery features without any additional mask supervision, and can outperform competing methods on FaceForensics++, Celeb-DF and DeeperForensics-l.0 datasets.
- Leveraging Large Language Models for Relevance Judgments in Legal Case Retrieval24
This work proposes a novel few-shot approach where LLMs assist in generating expert-aligned interpretable relevance judgments and demonstrates that with minimal expert supervision, this approach enables a large language model to acquire case analysis expertise and subsequently transfers this ability to a smaller model via annotation-based knowledge distillation.
- GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection23
A novel Geometry Uncertainty Propagation Network (GUPNet++) is proposed by modeling geometry projection in a probabilistic manner that models the uncertainty propagation relationship of the geometry projection during training, improving the stability and efficiency of the end-to-end model learning.
- Fluid Dynamics-Inspired Network for Infrared Small Target Detection23
A novel research routine is explored by abstracting the movement of pixels in the ISTD process as the flow of fluid in fluid dynamics (FD), and a new Fluid Dynamics-Inspired Network (FDI-Net) is devised for ISTD.
- Towards Intrinsic Common Discriminative Features Learning for Face Forgery Detection Using Adversarial Learning21
This work proposes a novel method which utilizes adversarial learning to eliminate the negative effect of different forgery methods and facial identities, which helps classification network to learn intrinsic common discriminative features for face forgery detection.
- Improve Unsupervised Pretraining for Few-label Transfer21
It is interestingly discover that only involving some unlabeled target domain into the unsupervised pretraining can improve the clustering quality, subsequently reducing the transfer performance gap with supervised pretraining.
- Exploiting Modality-Specific Features for Multi-Modal Manipulation Detection and Grounding19
This paper constructs a simple and novel transformer-based framework for multi-modal manipulation detection and grounding tasks and proposes an implicit manipulation query (IMQ) that adaptively aggregates global contextual cues within each modality using learnable queries, thereby improving the discovery of forged details.
- 18
- Multi-spectral Class Center Network for Face Manipulation Detection and Localization18
A novel Multi-Spectral Class Center Network (MSCCNet) is proposed for face manipulation detection and localization and a Multi-level Features Aggregation (MFA) module is proposed to employ more low-level forgery artifacts and structural textures.
- Towards More Unified In-Context Visual Understanding17
A new ICL framework for visual understanding with multi-modal output enabled is presented, capable of handling in-context vision understanding tasks with multimodal output in a unified pipeline and takes a further step toward unified multimodal in-context learning.
- Mixture-of-Noises Enhanced Forgery-Aware Predictor for Multi-Face Manipulation Detection and Localization15
This paper proposes a new framework, namely MoNFAP, specifically tailored for multi-face manipulation detection and localization, and establishes a comprehensive benchmark for multi-face detection and localization.
- 15
- 15
- 13
- 13
- 13
- 12
- 11
- Bootstrapping Audio-Visual Segmentation by Strengthening Audio Cues11
This work proposes AVSAC, a Bidirectional Audio-Visual Decoder with integrated bidirectional bridges, enhancing audio cues and fostering continuous interplay between audio and visual modalities, which narrows the modality imbalance, facilitating more effective learning of integrated audio-visual representations.
- High-performance blob-based iterative three-dimensional reconstruction in electron tomography using multi-GPUs11
Experimental results indicate that the multilevel parallel scheme combined with the asynchronous communication scheme and the blob-ELLR data structure allows efficient implementations of 3D reconstruction in ET on multi-GPUs.
- MFFI: Multi-Dimensional Face Forgery Image Dataset for Real-World Scenarios10
Benchmark evaluations show that MFFI outperforms existing public datasets in terms of scene complexity, cross-domain generalization capability, and detection difficulty gradients, and validate the technical advance and practical utility of MFFI in simulating real-world conditions.
- 8
- Towards Anytime Retrieval: A Benchmark for Anytime Person Re-Identification6
A unified model named Uni-AT is proposed, which comprises a multi-scenario ReID (MS-ReID) framework for scenario-specific features learning, a Mixture-of-Attribute-Experts (MoAE) module to alleviate inter-scenario interference, and a Hierarchical Dynamic Weighting (HDW) strategy to ensure balanced training across all scenarios.
- Evopose: A Recursive Transformer for 3D Human Pose Estimation with Kinematic Structure Priors6
A novel transformer-based model EvoPose is proposed to introduce the human body prior knowledge for 3D human pose estimation effectively and achieves a new state of the art on two most popular benchmarks, Human3.6M and MPI-INF-3DHP.
- 6
- 6
- Semantic Image Synthesis via Efficient Class-Adaptive Normalization6
An in-depth analysis of the effectiveness of this spatially-adaptive normalization is conducted and it is observed that its modulation parameters benefit more from semantic-awareness rather than spatial-adaptiveness, especially for high-resolution input masks.
- Rethinking Masked Data Reconstruction Pretraining for Strong 3D Action Representation Learning5
It is shown that contrastive learning can consistently boost the performance of model pre-trained by masked joint prediction under various settings, especially in the semi-supervised setting that has a very limited number of labeled samples.
- 5
- A fast calculation strategy of density function in ISAF reconstruction algorithm5
The experimental results on Psv-F simulated data indicate that the speed of calculating density function is increased almost two orders of magnitude and the speedup of the whole algorithm could reach 30 times, which could go up with the increase in the number of images and the requirement of accuracy.
- Multi-spectral Class Center Network for Face Manipulation Localization4
It is observed that multi-frequency spectrum information is effective for identifying tampered regions of forgery images and a novel Multi-spectral Class Center Network (MSCCNet) is proposed for face manipulation localization.
- Context-Aware Weakly Supervised Image Manipulation Localization With SAM Refinement4
A Context-Aware Boundary Localization (CABL) module is proposed to aggregate boundary features and learn context-inconsistency for localizing manipulated areas and a novel weakly supervised framework based on a dual-branch Transformer-CNN architecture is presented.
- 4
- High-Performance Blob-Based Iterative Reconstruction of Electron Tomography on Multi-GPUs4
Experimental results indicate that the multilevel parallel scheme allows efficient implementations of 3D reconstruction of ET on multi-GPUs, without loss any resolution.
- 3
- 3
- Affinity-Aware Relation Network for Oriented Object Detection in Aerial Images3
A novel and accessible Affinity-Aware Relation Network based on two-stage detectors based on two-stage detectors that achieves notable AP improvements as well as state-of-the-art performances on DOTA, HRSC2016 and UCAS-AOD datasets.
- 3
- 3
- 3
- Training-free Open-Vocabulary Semantic Segmentation via Diverse Prototype Construction and Sub-region Matching2
A novel training-free framework for OVSS that constructs diverse prototypes and performs fine-grained sub-region matching and leverages Large Language Models to guide image generation by descriptions of different attributes of categories and employs coarse-fine clustering to obtain diverse and robust part-level prototypes in the construction stage.
- Towards Good Generalizations for Diffusion Generated Image Detection Using Multiple Reconstruction Contrastive Learning2
This paper proposes Multiple Reconstruction Contrastive Learning (MRCL), which leverages multiple reconstruction residuals to enhance the generalizability of generated image detection and applies Dinov2-ViT with LoRA fine-tuning to extract fine-grained feature representations of origin images and their multiple VAE reconstructions.
- 2
- 2
- Training-Free In-Context Forensic Chain for Image Manipulation Detection and Localization1
The In-Context Forensic Chain (ICFC) is proposed, a training-free framework that leverages multi-modal large language models (MLLMs) for interpretable IML tasks and enables systematic exploitation of MLLM reasoning for image-level classification, pixel-level localization, and text-level interpretability.
- 1
- 1
- 1
- Three-Dimensional Reconstruction of Electron Tomography Using Graphic Processing Units (GPUs)1
A multilevel parallel scheme to perform iterative algorithm reconstruction using blob on GPUs and a matrix storage technique, called blobELL-R, suitable for GPUs, to address the large memory requirements of the weighted matrix.
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-15. 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.