Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks130 from public data
- 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.
- 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.
- Generative Cooperative Learning for Unsupervised Video Anomaly Detection236
This work proposes a novel unsupervised Generative Cooperative Learning (GCL) approach for video anomaly detection that exploits the low frequency of anomalies towards building a cross-supervision between a generator and a discriminator.
- 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.
- 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.
- 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.
- 72
- Pushing the boundaries of audiovisual word recognition using Residual Networks and LSTMs66
A deep learning architecture for lipreading and audiovisual word recognition is presented, which combines Residual Networks equipped with spatiotemporal input layers and Bidirectional LSTMs and further analysis on the utility of target word boundaries is provided.
- Alzheimer's disease: 3‐Dimensional MRI texture for prediction of conversion from mild cognitive impairment64
The main objective was to determine whether MRI texture could be used to predict conversion of MCI to AD.
- 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.
- Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment53
This work demonstrates that by carefully selecting a set of augmentations, a base detector can outperform existing methods for single domain generalization by a good margin and introduces a method to align detections from multiple views, considering both classification and localization outputs.
- Fusion and Orthogonal Projection for Improved Face-Voice Association53
This work hypothesize that enriched feature representation coupled with an effective yet efficient supervision is necessary in realizing a discriminative joint embedding space for improved face-voice association and proposes a light-weight, plug-and-play mechanism that exploits the complementary cues in both modalities to form enriched fused embeddings and clusters them based on their identity labels via orthogonality constraints.
- Realistic and Efficient Face Swapping: A Unified Approach with Diffusion Models52
This work proposes to reframe the face-swapping task as a self-supervised, train-time inpainting problem, enhancing the identity transfer while blending with the target image, and introduces a mask shuffling technique during inpainting training, which allows for a so-called universal model for swapping.
- 51
- ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks49
ThinkGeo, an agentic benchmark designed to evaluate LLM-driven agents on remote sensing tasks via structured tool use and multi-step planning, provides the first extensive testbed for evaluating how tool-enabled LLMs handle spatial reasoning in remote sensing.
- EcoTaskSched: a hybrid machine learning approach for energy-efficient task scheduling in IoT-based fog-cloud environments49
A novel ML-based EcoTaskSched model is proposed, which leverages deep learning for energy-efficient task scheduling in fog-cloud networks and is successfully applied to fog-cloud computing environments, increasing task handling efficiency and reducing energy consumption while maintaining the required QoS parameters.
- Synergy between Face Alignment and Tracking via Discriminative Global Consensus Optimization43
This work describes the very first, to the best of the knowledge, synergistic approach between detection and tracking which completely eliminates drifting from face tracking, and does not merely perform tracking-by-detection.
- The Canadian ALS Neuroimaging Consortium (CALSNIC) - a multicentre platform for standardized imaging and clinical studies in ALS38
The Canadian ALS Neuroimaging Consortium (CALSNIC) was founded to develop and evaluate advanced MRI-based biomarkers that delineate biological heterogeneity, track disease progression, and predict survival in a large and heterogeneous sample of ALS patients.
- Single-branch Network for Multimodal Training35
This work proposes a novel single-branch network capable of learning discriminative representation of unimodal as well as multimodal tasks without changing the network and demonstrates the superiority of this network over the existing methods in a wide range of experiments.
- Multiclass Confidence and Localization Calibration for Object Detection35
This paper proposes a new train-time technique for calibrating modern object detection methods that is capable of jointly calibrating multiclass confidence and box localization by leveraging their predictive uncertainties.
- 34
- 32
- 32
- TRIC-track: Tracking by Regression with Incrementally Learned Cascades32
This paper proposes to use cascaded regression with incremental learning to track generic objects without any prior knowledge of an object's structure or appearance by replacing local matching of an appearance model by direct prediction of the displacement between local image patches and part locations.
- Rich Semantics Improve Few-Shot Learning30
This work creates a bottleneck visual feature which is then used to generate language descriptions of the classes as an auxiliary task during training, and develops a Transformer based forward and backward encoding mechanism to relate visual and semantic tokens that can encode intricate relationships between the two modalities.
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.