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
- María VanrellSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works378 from public data
- Restormer: Efficient Transformer for High-Resolution Image Restoration4,635
This work proposes an efficient Transformer model by making several key designs in the building blocks (multi-head attention and feed-forward network) such that it can capture long-range pixel interactions, while still remaining applicable to large images.
- Transformers in Vision: A Survey3,900
This survey aims to provide a comprehensive overview of the Transformer models in the computer vision discipline with an introduction to fundamental concepts behind the success of Transformers, i.e., self-attention, large-scale pre-training, and bidirectional feature encoding.
- ECO: Efficient Convolution Operators for Tracking2,708
This work revisit the core DCF formulation and introduces a factorized convolution operator, which drastically reduces the number of parameters in the model, and a compact generative model of the training sample distribution that significantly reduces memory and time complexity, while providing better diversity of samples.
- Multi-Stage Progressive Image Restoration2,345
This paper proposes a novel synergistic design that can optimally balance these competing goals in image restoration tasks, that progressively learns restoration functions for the degraded inputs, thereby breaking down the overall recovery process into more manageable steps.
- Accurate Scale Estimation for Robust Visual Tracking2,087
This paper presents a novel approach to robust scale estimation that can handle large scale variations in complex image sequences and shows promising results in terms of accuracy and efficiency.
- Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking1,770
Discriminative Correlation Filters have demonstrated excellent performance for visual object tracking and the key to their success is the ability to efficiently exploit available negative data.
- 1,512
- ATOM: Accurate Tracking by Overlap Maximization1,509
This work proposes a novel tracking architecture, consisting of dedicated target estimation and classification components, and introduces a classification component that is trained online to guarantee high discriminative power in the presence of distractors.
- Transformers in medical imaging: A survey1,338
This survey surveys the use of Transformers in medical image segmentation, detection, classification, restoration, synthesis, registration, clinical report generation, and other tasks and develops taxonomy for each application.
- Discriminative Scale Space Tracking1,312
This paper proposes a novel scale adaptive tracking approach by learning separate discriminative correlation filters for translation and scale estimation in a tracking-by-detection framework that obtains the top rank in performance by outperforming 19 state-of-the-art trackers on OTB and 37 state of theart tracker on VOT2014.
- MaPLe: Multi-modal Prompt Learning1,242
The design promotes strong coupling between the vision-language prompts to ensure mutual synergy and discourages learning independent uni-modal solutions, and the effectiveness of the approach is evaluated on three representative tasks of generalization to novel classes, new target datasets and unseen domain shifts.
- Learning Enriched Features for Real Image Restoration and Enhancement1,052
This paper presents a novel architecture with the collective goals of maintaining spatially-precise high-resolution representations through the entire network and receiving strong contextual information from the low- resolution representations, named as MIRNet.
- 975
- The Sixth Visual Object Tracking VOT2018 Challenge Results804
The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative; results of over eighty trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years.
- The Visual Object Tracking VOT2016 Challenge Results776
The Visual Object Tracking challenge VOT2016 goes beyond its predecessors by introducing a new semi-automatic ground truth bounding box annotation methodology and extending the evaluation system with the no-reset experiment.
- Towards Open World Object Detection654
This work proposes a novel computer vision problem called ORE: Open World Object Detector, which is based on contrastive clustering and energy based unknown identification, and finds that identifying and characterising unknown instances helps to reduce confusion in an incremental object detection setting.
- Learning Enriched Features for Fast Image Restoration and Enhancement653
The approach learns an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details, and achieves state-of-the-art results for a variety of image processing tasks.
- GLaMM: Pixel Grounding Large Multimodal Model594
This work presents Grounding LMM (GLaMM), the first model that can generate natural language responses seamlessly in-tertwined with corresponding object segmentation masks and is flexible enough to accept both textual and optional visual prompts (region of interest) as input.
- The Visual Object Tracking VOT2014 Challenge Results588
The Visual Object Tracking challenge 2014, VOT2014, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance and introduces a new dataset with full annotation of targets by rotated bounding boxes and per-frame attribute.
- GeoChat:Grounded Large Vision-Language Model for Remote Sensing576
This work proposes GeoChat - the first versatile remote sensing VLM that offers multitask conversational capabilities with high-resolution RS images, and generates a novel RS multimodal instruction-following dataset by extending image-text pairs from existing diverse RS datasets.
- UNETR++: Delving Into Efficient and Accurate 3D Medical Image Segmentation496
This paper proposes a 3D medical image segmentation approach that offers both high-quality segmentation masks as well as efficiency in terms of parameters, compute cost, and inference speed and introduces a novel efficient paired attention block that efficiently learns spatial and channel-wise discriminative features using a pair of inter-dependent branches based on spatial and channel attention.
- 496
- Unveiling the Power of Deep Tracking484
This paper proposes a novel adaptive fusion approach that leverages the complementary properties of deep and shallow features to improve both robustness and accuracy in generic object tracking.
- Self-regulating Prompts: Foundational Model Adaptation without Forgetting460
This work introduces a self-regularization framework for prompting called PromptSRC (Prompting with Self-regulating Constraints), the first regularization framework for prompt learning that avoids overfitting by jointly attending to pre-trained model features, the training trajectory during prompting, and the textual diversity.
- CycleISP: Real Image Restoration via Improved Data Synthesis460
This paper presents a framework that models camera imaging pipeline in forward and reverse directions that allows any number of realistic image pairs for denoising both in RAW and sRGB spaces and achieves the state-of-the-art performance on real camera benchmark datasets.
- 443
- 434
- Learning the Model Update for Siamese Trackers431
This work uses a convolutional neural network, called UpdateNet, which given the initial template, the accumulated template and the template of the current frame aims to estimate the optimal template for the next frame, and demonstrates the generality of the proposed approach by applying it to two Siamese trackers.
- Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking430
This work proposes a novel generic approach for alleviating the problem of corrupted training samples in tracking-by-detection frameworks by minimizing a single loss over both the target appearance model and the sample quality weights.
- Object-Centric Auto-Encoders and Dummy Anomalies for Abnormal Event Detection in Video425
An unsupervised feature learning framework based on object-centric convolutional auto-encoders to encode both motion and appearance information is introduced and a supervised classification approach based on clustering the training samples into normality clusters is proposed.
- 417
- 416
- A Self-supervised Approach for Adversarial Robustness385
This paper proposes a self-supervised adversarial training mechanism in the input space that provides significant robustness against the unseen adversarial attacks and can be deployed as a plug-and-play solution to protect a variety of vision systems, as it demonstrates for the case of classification, segmentation and detection.
- Anomaly Detection in Video via Self-Supervised and Multi-Task Learning373
This paper is the first to approach anomalous event detection in video as a multi-task learning problem, integrating multiple self-supervised and knowledge distillation proxy tasks in a single architecture and outperforms the state-of-the-art methods on three benchmarks.
- Deep Projective 3D Semantic Segmentation366
This work states that semantic segmentation of 3D point clouds is a challenging problem with numerous real-world applications that requires voxelizations of the underlying point cloud data, leading to decreased spatial resolution and increased memory consumption.
- 356
- 324
- 317
- Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection311
The proposed self-supervised block is generic and can easily be incorporated into various state-of-the-art anomaly detection methods, providing empirical evidence that shows considerable performance improvements on MVTec AD, Avenue, and ShanghaiTech.
- OW-DETR: Open-world Detection Transformer294
This work introduces a novel end-to-end transformer-based framework, OW-DETR, for open-world object detection that explicitly encodes multi-scale contextual information, possesses less inductive bias, enables knowledge transfer from known classes to the unknown class and can better discriminate between unknown objects and background.
- 294
- Fine-tuned CLIP Models are Efficient Video Learners287
This work shows that a simple Video Fine-tuned CLIP (ViFi-CLIP) baseline is generally sufficient to bridge the domain gap from images to videos, and proposes a ‘bridge and prompt’ approach that first uses fine-tuning to bridgeThe domain gap and then learns prompts on language and vision side to adapt CLIP representations.
- Binary patterns encoded convolutional neural networks for texture recognition and remote sensing scene classification286
This paper shows that Local Binary Patterns (LBP) encoded CNN models, codenamed TEX-Nets, trained using mapped coded images with explicit LBP based texture information provide complementary information to the standard RGB deep models.
- 281
- SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications279
This work introduces a novel efficient additive attention mechanism that effectively replaces the quadratic matrix multiplication operations with linear element-wise multiplications and shows that the key-value interaction can be replaced with a linear layer without sacrificing any accuracy.
- 258
- Learning Human-Object Interaction Detection Using Interaction Points256
This paper proposes a novel fully-convolutional approach that directly detects the interactions between human-object pairs and predicts interaction points, which directly localize and classify the inter-action.
- A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video242
A background-agnostic framework that learns from training videos containing only normal events, and provides region-based and track-based annotations for two large-scale abnormal event detection data sets from the literature, namely ShanghaiTech and Subway.
- Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook224
This survey presents a systematic and thorough review of more than 90 DCFs and Siamese trackers, based on results in nine tracking benchmarks, and distinguishes and comprehensively review the shared as well as specific open research challenges in both these tracking paradigms.
- Confidence Propagation through CNNs for Guided Sparse Depth Regression223
This paper proposes an algebraically-constrained normalized convolution layer for CNNs with highly sparse input that has a smaller number of network parameters compared to related work and introduces the use of output confidence as an auxiliary information to improve the results.
- Mask-Guided Attention Network for Occluded Pedestrian Detection223
A novel mask-guided attention network is introduced that emphasizes on visible pedestrian regions while suppressing the occluded ones by modulating full body features and it is empirically demonstrated that coarse-level segmentation annotations provide reasonable approximation to their dense pixel-wise counterparts.
- Multi-Modal Fusion for End-to-End RGB-T Tracking219
This work proposes an end-to-end tracking framework for fusing the RGB and TIR modalities in RGB-T tracking, and evaluates the effectiveness of modality fusion in each of the main components in DiMP, i.e. feature extractor, target estimation network, and classifier.
- Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection215
This work proposes to address the gap between object and image-centric representations in the OVD setting by performing object-centric alignment of the language embeddings from the CLIP model using a pseudo-labeling process that provides high-quality object proposals and helps expand the vocabulary during training.
- PromptIR: Prompting for All-in-One Blind Image Restoration212
This work presents a prompt-based learning approach, PromptIR, for All-In-One image restoration that can effectively restore images from various types and levels of degradation, and uses prompts to encode degradation-specific information, which is then used to dynamically guide the restoration network.
- MineGAN: Effective Knowledge Transfer From GANs to Target Domains With Few Images211
This work proposes a novel knowledge transfer method for generative models based on mining the knowledge that is most beneficial to a specific target domain, either from a single or multiple pretrained GANs, and shows that it effectively transfers knowledge to domains with few target images, outperforming existing methods.
- SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation200
A fast single-stage instance segmentation method that preserves instance-specific spatial information by separating mask prediction of an instance to different sub-regions of a detected bounding-box, leading to improved mask predictions and a mask alignment weighting loss and a feature alignment scheme to better correlate mask prediction with object detection.
- A Generative Appearance Model for End-To-End Video Object Segmentation200
This work proposes a network architecture that learns a powerful representation of the target and background appearance in a single forward pass, and outperforms all published approaches on the large-scale YouTube-VOS dataset.
- UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection191
UB-normal is the first video anomaly detection benchmark to allow a fair head-to-head comparison between one-class open-set models and supervised closed- set models, and empirical evidence showing that UB-normal can enhance the performance of a state-of-the-art anomaly detection framework on two prominent data sets, Avenue and ShanghaiTech.
- Person Image Synthesis via Denoising Diffusion Model186
This work shows how denoising diffusion models can be applied for high-fidelity person image synthesis with strong sample diversity and enhanced mode coverage of the learnt data distribution and introduces a ‘texture diffusion module’ based on cross-attention to accurately model the correspondences between appearance and pose information available in source and target images.
- 3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization183
This work proposes a framework, called 3C-Net, which only requires video-level supervision (weak supervision) in the form of action category labels and the corresponding count to learn discriminative action features with enhanced localization capabilities.
- iTAML: An Incremental Task-Agnostic Meta-learning Approach176
A novel meta-learning approach that seeks to maintain an equilibrium between all the encountered tasks, ensured by a new meta-update rule which avoids catastrophic forgetting and is task-agnostic.
- Painting-91: a large scale database for computational painting categorization176
It is shown that state-of-the-art computer vision methods can correctly classify 50 % of unseen paintings to its painter in a large dataset and correctly attribute its artistic style in over 60 % of the cases.
- Foundational Models Defining a New Era in Vision: A Survey and Outlook172
A comprehensive review of emerging foundational models in computer vision, including typical architecture designs to combine different modalities, training objectives, pre-training datasets, fine-tuning mechanisms, and the common prompting patterns; textual, visual, and heterogeneous.
- Random Path Selection for Continual Learning168
This paper proposes a random path selection algorithm, called RPS-Net, that progressively chooses optimal paths for the new tasks while encouraging parameter sharing and reuse and proposes a simple controller to dynamically balance the model plasticity.
- 168
- SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation162
A simple encoder-decoder for open-vocabulary semantic segmentation, which comprises a hierarchical encoder-based cost map generation and a gradual fusion decoder with category early rejection, and a category early rejection scheme in the decoder that rejects many no-existing categories at the early layer of decoder.
- Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting161
This work proposes a multimodal prompt learning scheme that works to balance the supervised and zero- shot performance under a single unified training and can achieve state-of-the-art zero-shot performance on Kinetics-600, HMDB51 and UCF101 while remaining competitive in the supervised setting.
- Spatio-temporal Relation Modeling for Few-shot Action Recognition159
A novel few-shot action recognition framework, STRM, which enhances class-specific feature discrim-inability while simultaneously learning higher-order temporal representations and introduces a query-class similarity classifier on the patch-level enriched features to enhance class- specific feature dis-criminability.
- From Handcrafted to Deep Features for Pedestrian Detection: A Survey158
An extensive review of single-spectral pedestrian detection that includes handcrafted features based methods and deep features based approaches is presented and it is found that hand crafted features with large freedom degrees in shape and space have better performance.
- Learning Fast and Robust Target Models for Video Object Segmentation158
This work proposes a novel VOS architecture consisting of two network components, exclusively trained offline, designed to process the coarse scores into high quality segmentation masks, and achieves favorable performance, while operating at higher frame-rates compared to state-of-the-art.
- Out-Of-Distribution Detection for Generalized Zero-Shot Action Recognition155
This paper is the first to propose an out-of-distribution detector based GZSL framework for action recognition in videos that determines whether the video features belong to a seen or unseen action category and outperforms the baseline.
- Distilled Siamese Networks for Visual Tracking148
This model is intuitively inspired by the one teacher versus multiple students learning method typically employed in schools and contains a single teacher-student distillation module and a student-student knowledge sharing mechanism that is designed using a tracking-specific distillation strategy to transfer knowledge from a teacher to students.
- Fine-Grained Recognition: Accounting for Subtle Differences between Similar Classes147
The main requisite for fine-grained recognition task is to focus on subtle discriminative details that make the subordinate classes different from each other, and this work proposes to explicitly force the network to find the subtle differences among closely related classes.
- XrayGPT: Chest Radiographs Summarization using Large Medical Vision-Language Models145
This paper introduces XrayGPT, a conversational medical vision-language (VLMs) model that can analyze and answer open-ended questions about chest radiographs, and aligns both medical visual encoder with a fine-tuned LLM to possess visual conversation abilities, grounded in an understanding of radiographs and medical knowledge.
- 145
- Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning142
This work proposes a novel training mechanism that simultaneously enforces equivariance and invariance to a general set of geometric transformations and shows that even without knowledge distillation this proposed method can outperform current state-of-the-art FSL methods on five popular benchmark datasets.
- Incremental Object Detection via Meta-Learning140
A meta-learning approach that learns to reshape model gradients, such that information across incremental tasks is optimally shared ensures a seamless information transfer via a meta-learned gradient preconditioning that minimizes forgetting and maximizes knowledge transfer.
- PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery139
This work proposes contrastive affinity learning to calibrate semantic representations based on the authors' iterative semi-supervised affinity graph generation method for semantically-enhanced supervision and proposes a discriminative prompt regularization loss to reinforce semantic discriminativeness of prompt-adapted pre-trained vision transformer for refined affinity relationships.
- 139
- Class-Agnostic Object Detection with Multi-modal Transformer138
This paper advocates that existing methods lack a top-down supervision signal governed by human-understandable semantics and demonstrates that Multi-modal Vision Transformers (MViT) trained with aligned image-text pairs can effectively bridge this gap.
- Deep Contextual Attention for Human-Object Interaction Detection138
This work proposes a contextual attention framework for human-object interaction detection that leverages context by learning contextually-aware appearance features for human and object instances and adaptively selects relevant instance-centric context information to highlight image regions likely to contain human- object interactions.
- Object Counting and Instance Segmentation With Image-Level Supervision136
This work is the first to propose image-level supervised density map estimation for common object counting and demonstrate its effectiveness in image- level supervised instance segmentation and outperforms existing methods, including those using instance-level supervision, on both datasets for common objects counting.
- Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery135
The proposed SatMAE++ with multi-scale pre-training is equally effective for both optical as well as multi-spectral imagery and achieves mean average precision (mAP) gain of 2.5% for multi-label classification task on BigEarthNet dataset.
- Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection132
A novel self-supervised masked convolutional transformer block (SSMCTB) that comprises the reconstruction-based functionality at a core architectural level and is extremely flexible, enabling information masking at any layer of a neural network and being compatible with a wide range of neural architectures.
- Remote Sensing Change Detection With Transformers Trained From Scratch129
This work develops an end-to-end CD approach with transformers that is trained from scratch and yet achieves state-of-the-art performance on five benchmarks, and introduces a change-enhanced feature fusion (CEFF) module to fuse the features from input image pairs by performing a per-channel re-weighting.
- Burst Image Restoration and Enhancement129
The central idea is to create a set of pseudo-burst features that combine complimentary information from all the input burst frames to seamlessly exchange information, and the approach initially extracts pre-processed features from each burst frame and matches them using an edge-boosting burst alignment module.
- 129
- Self-supervised Knowledge Distillation for Few-shot Learning127
This paper proposes a simple approach to improve the representation capacity of deep neural networks for few-shot learning tasks, and shows that, even in the first stage, self-supervision can outperform current state-of-the-art methods.
- The Ninth Visual Object Tracking VOT2021 Challenge Results127
The Visual Object Tracking challenge VOT2021 is the ninth annual tracker benchmarking activity organized by the VOT initiative; results of 71 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in recent years.
- Modulating Shape Features by Color Attention for Object Recognition125
This paper presents a novel method for recognizing object categories when using multiple cues by separately processing the shape and color cues and combining them by modulating the shape features by category-specific color attention.
- 123
- ELGC-Net: Efficient Local–Global Context Aggregation for Remote Sensing Change Detection118
This work proposes an efficient change detection (CD) framework, efficient global and local context aggregation network (ELGC-Net), which leverages rich contextual information to precisely estimate change regions while reducing the model size, and introduces ELGC-Net-LW, a lighter variant with significantly reduced computational complexity, suitable for resource-constrained settings.
- Self-supervised Video Transformer118
This approach is the first to alleviate the dependency on negative samples or dedicated memory banks in Self-supervised Video Transformer (SVT), and supports slow-fast video processing within a single architecture using dynamically adjusted positional encoding and supports longterm relationship modeling along spatiotemporal dimensions.
- Multimodal Multi-Head Convolutional Attention with Various Kernel Sizes for Medical Image Super-Resolution116
A novel multi-modal multi-head convolutional attention module to super-resolving CT and MRI scans that uses the convolution operation to perform joint spatial-channel attention on multiple concatenated input tensors and shows the superiority of the attention module over the state-of-the-art attention mechanisms used in super-resolution.
- Image colorization: A survey and dataset115
This article presents a comprehensive survey of recent state-of-the-art colorization using deep learning algorithms, describing their fundamental block architectures in terms of skip connections, input etc as well as optimizers, loss functions, training protocols, and training data etc.
- 115
- 114
- 113
- Coloring Action Recognition in Still Images113
The experiments demonstrate that incorporating color information considerably improves recognition performance, and that a descriptor based on color names outperforms pure color descriptors and that late fusion of color and shape information outperforms other approaches on action recognition.
- EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues110
EarthDial is introduced, a conversational assistant specifically designed for Earth Observation (EO) data, transforming complex, multi-sensory Earth observations into interactive, natural language dialogues, and outperforms existing generic and domain-specific models, achieving better generalization across various EO tasks.
- 110
- On Generating Transferable Targeted Perturbations104
A new generative approach for highly transferable targeted perturbations (TTP) that not only aligns the global distributions of source and target images, but also matches the local neighbourhood structure between the two domains.
- Orthogonal Projection Loss104
OPL augments the properties of CE loss and directly enforces inter-class separation alongside intra-class clustering in the feature space through orthogonality constraints on the mini-batch level and offers unique advantages e.g., no additional learnable parameters, does not require careful negative mining and is not sensitive to the batch size.
- 99
- Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors97
An efficient abnormal event detection model based on a lightweight masked auto-encoder applied at the video frame level that achieves an excellent trade-off between speed and accuracy, obtaining competitive AUC scores, while processing 1655 FPS is proposed.
- Faster Diffusion: Rethinking the Role of UNet Encoder in Diffusion Models97
It is found that encoder features change gently, whereas the decoder features exhibit substantial variations across different time-steps, which inspired us to conduct the first comprehensive study of the UNet encoder.
- 97
- NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results94
The NTIRE 2022 challenge was to super-resolve an input image with a magnification factor of ×4 based on pairs of low and corresponding high resolution images and the aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics.
- Learning to Fuse Asymmetric Feature Maps in Siamese Trackers94
The asymmetric convolution (ACM) is proposed, which learns to better capture the se-mantic correlation information in offline training on large-scale data and can easily be integrated into existing Siamese trackers based on DW-XCorr or XCorr.
- 93
- Airline ticket price and demand prediction: A survey92
This paper introduces and discusses the concept of using social media data for ticket/demand prediction and shows that models on both sides rely on limited set of features such as historical ticket price data, ticket purchase date and departure date.
- Handwriting Transformers90
A novel transformer-based styled handwritten text image generation approach, HWT, that strives to learn both style-content entanglement as well as global and local style patterns, and is the first to introduce a transformer- based network for styling handwritten text generation.
- Deep motion features for visual tracking90
To the best of the knowledge, this paper is the first to propose fusing appearance information with deep motion features for visual tracking, and it is shown that hand-crafted, deep RGB, and deepmotion features contain complementary information.
- Sentence-level Prompts Benefit Composed Image Retrieval89
This work demonstrates that learning an appropriate sentence-level prompt for the relative caption (SPRC) is sufficient for achieving effective composed image retrieval and proposes to leverage pretrained V-L models, e.g., BLIP-2, to generate sentence- level prompts.
- 89
- PSTR: End-to-End One-Step Person Search With Transformers88
The proposed PSTR is the first to propose an end-to-end one-step transformer-based person search framework that jointly performs person detection and re-identification (re-id) in a single architecture and sets a new state-of-the-art on both benchmarks.
- Burstormer: Burst Image Restoration and Enhancement Transformer79
This work proposes Burstormer: a novel transformer-based architecture for burst image restoration and enhancement that outperforms state-of-the-art methods on burst super-resolution, burst denoising and burst low-light enhance-ment.
- 76
- Synthesizing the Unseen for Zero-Shot Object Detection75
This work proposes a novel generative model that uses class-semantics to not only generate the features but also to discriminatively separate them, using a unified model, to synthesize visual features for unseen classes, so that the model learns both seen and unseen objects in the visual domain.
- 72
- Discriminative Region-based Multi-Label Zero-Shot Learning70
This work proposes an alternate approach towards region-based discriminability-preserving multi-label zero-shot classification that maintains the spatial resolution to preserve region-level characteristics and utilizes a bi-level attention module (BiAM) to enrich the features by incorporating both region and scene context information.
- D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations69
A novel loss formulation is introduced, which jointly enhances the discriminability of latent embeddings and robustness of the output temporal class activations with respect to foreground-background noise caused by weak supervision, in a weakly-supervised temporal action localization framework, called D2-Net.
- The Thermal Infrared Visual Object Tracking VOT-TIR2016 Challenge Results66
A significant general improvement of results has been observed, which partly compensate for the more difficult sequences introduced into the dataset in VOT-TIR2016.
- Discriminative compact pyramids for object and scene recognition65
Comparison to clustering based on agglomerative information bottleneck (AIB) shows that the method obtains superior results at significantly lower computational costs and the optimal combination of multiple features in the context of the compact pyramid representation is investigated.
- AnimalWeb: A Large-Scale Hierarchical Dataset of Annotated Animal Faces61
A large-scale, hierarchical annotated dataset of animal faces, featuring 22.4K faces from 350 diverse species and 21 animal orders across biological taxonomy is introduced, showing its challenging nature, unique attributes and present definite prospects for novel, adaptive, and generalized face-oriented CV algorithms.
- PSC-Net: learning part spatial co-occurrence for occluded pedestrian detection61
The proposed PSC-Net contains a dedicated module that is designed to explicitly capture both inter and intra-part co-occurrence information of different pedestrian body parts through a graph convolutional network (GCN).
- Portmanteau Vocabularies for Multi-Cue Image Representation60
A novel technique for feature combination in the bag-of-words model of image classification that uses Information theoretic vocabulary compression to find discriminative combinations of cues and the resulting vocabulary of portmanteau words is compact, has the cue binding property, and supports individual weighting of cues in the final image representation.
- Energy-based Latent Aligner for Incremental Learning59
This work proposes ELI: Energy-based Latent Aligner for Incremental Learning, which first learns an energy manifold for the latent representations such that previous task latents will have low energy and the current task latent values have high energy.
- Density Adaptive Point Set Registration58
The density-adaptive registration successfully handles severe density variations commonly encountered in terrestrial Lidar applications and outperforms state-of-the-art probabilistic methods for multi-view registration, without the need of re-sampling.
- Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning57
A progressive semantic-guided vision transformer for zero-shot learning (dubbed ZSLViT), which introduces semantic-embedded token learning to improve the visual-semantic correspondences via semantic enhancement and discover the semantic-related visual tokens explicitly with semantic-guided token attention.
- 57
- 55
- Compact color–texture description for texture classification55
This paper shows that combining multiple texture description methods significantly improves the recognition performance compared to using a single best texture method alone, and proposes to use information theoretic compression approach to compress high-dimensional multi-texture features into a compact heterogeneous texture representation.
- One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt54
This paper proposes a novel training-free method for consistent text-to-image (T2I) generation, termed "One-Prompt-One-Story", which concatenates all prompts into a single input for T2I diffusion models, initially preserving character identities.
- Semi-Supervised Learning for Few-Shot Image-to-Image Translation54
This work proposes applying semi-supervised learning via a noise-tolerant pseudo-labeling procedure, and applies a cycle consistency constraint to further exploit the information from unlabeled images, either from the same dataset or external.
- 54
- Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference52
This paper conducts a comprehensive study of the UNet encoder and empirically analyze the encoder features, which provides insights regarding their changes during the inference process, and finds that encoder features change minimally, whereas the decoder features exhibit substantial variations across different time-steps.
- Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning51
This work proposes a novel Visual-Augmented Dynamic Semantic prototype method (termed VADS) to boost the generator to learn accurate semantic-visual mapping by fully exploiting the visual-augmented knowledge into semantic conditions.
- Generative Multi-Label Zero-Shot Learning51
This work is the first to tackle the problem of multi-label feature synthesis in the (generalized) zero-shot setting with a cross-level fusion-based generative approach, which outperforms the state-of-the-art on three zero- shot benchmarks: NUS-WIDE, Open Images and MS COCO.
- 51
- 49
- CyTran: A cycle-consistent transformer with multi-level consistency for non-contrast to contrast CT translation47
A novel approach to translate unpaired contrast CT scans to non-contrast CT scans and the other way around, based on cycle-consistent generative adversarial convolutional transformers, for short, CyTran, which outperforms all competing methods and can be employed as a preliminary step to improve a state-of-the-art medical image alignment method.
- Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition47
Video-FocalNet is based on a spatiotemporal focal modulation architecture that reverses the interaction and aggregation steps of self-attention for better efficiency and performs favorably well against the state-of-the-art transformer-based models for video recognition on five large-scale datasets.
- 46
- 46
- AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results43
This paper introduces the real image Super-Resolution challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020, and gauges the state-of-the-art approaches for real image SR in terms of PSNR and SSIM.
- 42
- Learning digital camera pipeline for extreme low-light imaging42
A new loss function is proposed that exploits the characteristics of both pixel-wise and perceptual metrics, enabling the deep neural network to learn the camera processing pipeline to transform the short-exposure, low-light RAW sensor data to well-exposed sRGB images.
- Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection40
This paper proposes a Discriminative co-salient and background Mining Transformer framework based on several economical multi-grained correlation modules to explicitly mine both co- saliency and background information and effectively model their discrimination.
- 39
- 38
- Count- and Similarity-Aware R-CNN for Pedestrian Detection35
A count-weighted detection loss function that assigns higher weights to the detection errors occurring at highly overlapping pedestrians, and a count-and-similarity branch within the two-stage detection framework, which predicts pedestrian count as well as proposal similarity to identify distinct proposals.
- 34
- 34
- Deep motion and appearance cues for visual tracking32
Generic visual tracking is a challenging computer vision problem, with numerous applications, and most existing approaches rely on appearance information by employing either hand-crafted features or de-crowding techniques.
- Coloring Channel Representations for Visual Tracking32
This work has shown that biologically-inspired channel representations have shown to provide promising results in many applications ranging from autonomous driving to visual tracking, and can be alleviated by constructing robust, discriminative and computationally efficient visual features.
- 29
- 28
- 28
- The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report27
This paper reviews the NTIRE 2026 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results and gauges the state-of-the-art results for efficient single-image super-resolution.
- 26
- 26
- 25
- 24
- How Good is Google Bard’s Visual Understanding? An Empirical Study on Open Challenges22
This study focuses on 15 diverse task scenarios encompassing regular, camouflaged, medical, under-water and remote sensing data to comprehensively evaluate Google Bard’s performance, and indicates that Bard still struggles in these vision scenarios.
- 22
- 22
- 22
- Stylized Adversarial Defense21
This work uses the style and content information of the target sample from another class, alongside its class-boundary information, to create adversarial perturbations, and proposes a max-margin adversarial training approach that minimizes the distance between source image and its adversary and maximizes thedistance between the adversary and the target image.
- 21
- 21
- 19
- 18
- 18
- 18
- 18
- 17
- 17
- 17
- 16
- Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks16
Agent-X is introduced, a large-scale benchmark for evaluating vision-centric agents multi-step and deep reasoning capabilities in real-world, multimodal settings and proposes a fine-grained, step-level evaluation framework that assesses the correctness and logical coherence of each reasoning step and the effectiveness of tool usage throughout the task.
- 16
- 16
- 16
- InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration15
Treating low-quality images as the intermediate state of LCM, InterLCM achieves a balance between fidelity and quality by starting from earlier LCM steps and incorporates a Visual Module to extract visual features and a Spatial Encoder to capture spatial details, enhancing the fidelity of restored images.
- 15
- 15
- 15
- 14
- 14
- 13
- 13
- 13
- 13
- 13
- 13
- 12
- 12
- 12
- 12
- 11
- 11
- 11
- 11
- 11
- 10
- 10
- 9
- 9
- 9
- 9
- 9
- 8
- LawDIS: Language-Window-Based Controllable Dichotomous Image Segmentation8
This work presents LawDIS, a language-window-based controllable dichotomous image segmentation (DIS) framework that produces high-quality object masks and significantly outperforms 11 cutting-edge methods across all metrics.
- 8
- 8
- 8
- 8
- 8
- 8
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- Deep Learning in Concealed Dense Prediction6
This article introduces and review a family of complex tasks, termed Concealed Dense Prediction (CDP), which has great value in agriculture, industry, etc and develops a taxonomy based on concealment counteracting to summarize deep learning efforts in CDP.
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- Hierarchical Visual Prompt Learning for Continual Video Instance Segmentation3
A novel Hierarchical Visual Prompt Learning (HVPL) model is developed that overcomes catastrophic forgetting of previous categories from both frame-level and video-level perspectives and proves to be more effective than baseline approaches.
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- Connecting dreams with visual brainstorming instruction2
This paper presents DreamConnect, employing a dual-stream diffusion framework to manipulate visually stimulated brain signals, and demonstrates the efficacy of the method to accurately direct human brain signals in desired directions, ultimately enabling concept manipulation through direct manipulation of the functional magnetic resonance imaging signals.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- Crafting Your Evolving Dreams: Concept-Incremental Versatile Customization1
This work develops a novel Continually Customizable Diffusion Model (CCDM), enabling users to perform concept-incremental versatile customization, and proposes a controllable regional context synthesis strategy that performs multi-concept composition in alignment with user-provided conditions.
- 1
- MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning1
A vision-centric agent tuning framework that automatically synthesizes multimodal trajectories, generates step-wise preference pairs, and trains a VLM controller for robust tool-use reasoning, demonstrating scalable and effective multimodal tool use.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Guidance Through Surrogate: Toward a Generic Diagnostic Attack1
The effect of label smoothing on AT is analyzed as one of the potential causes of gradient masking, leading to a novel attack dubbed guided projected gradient attack (G-PGA), which can be used as a diagnostic tool to reveal elusive robustness due to gradient masking in adversarial defenses.
- 1
- 1
- 1
- 1
- 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 2026-10-13. 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.