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
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works40 from public data
- 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.
- 496
- 434
- 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.
- Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to End142
This work proposes a novel approach to identify disturbed measurements in the input by learning an input confidence estimator in a self-supervised manner based on the normalized convolutional neural networks (NCNNs), and proposes a probabilistic version of NCNNs that produces a statistically meaningful uncertainty measure for the final prediction.
- 93
- 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.
- Zero-Shot 3D Shape Correspondence44
This work introduces a fully automatic method that exploits the exceptional reasoning capabilities of recent foundation models in language and vision to tackle difficult shape correspondence problems and produces highly plausible results in a zero-shot manner, especially between strongly non-isometric shapes.
- Unpaired Thermal to Visible Spectrum Transfer Using Adversarial Training31
This paper proposes an unsupervised Generative Adversarial Network (GAN) which trains on unpaired TIR and VIS images to transform TIR images into realistic visible spectrum (VIS) images and was shown to generalize very well when evaluated on a new dataset of new environments.
- Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generation20
Experiments show that the proposed diffusion-based approach for Text-to-Image (T2I) generation with interactive 3D layout control can generate complicated scenes based on 3D layouts, boosting the object generation success rate over the standard depth-conditioned T2I methods by 2x.
- Placeit3d: Language-Guided Object Placement in Real 3D Scenes13
This work inaugurate the task of Language-Guided Object Placement in Real 3D Scenes by introducing a benchmark and evaluation protocol, releasing a dataset for training multi-modal large language models (MLLMs), and establishing a first nontrivial baseline.
- Normalized Convolution Upsampling for Refined Optical Flow Estimation13
The Normalized Convolution UPsampler (NCUP), an efficient joint upsampling approach to produce the full-resolution flow during the training of optical flow CNNs, is proposed and shows better generalization capabilities than RAFT when trained and evaluated on different datasets.
- Zero-Shot Video Semantic Segmentation based on Pre-Trained Diffusion Models12
This work introduces the first zero-shot approach for Video Semantic Segmentation (VSS) based on pre-trained diffusion models, and proposes building a scene context model based on the diffusion features, where the model is autoregressively updated to adapt to scene changes.
- PartEdit: Fine-Grained Image Editing using Pre-Trained Diffusion Models10
This work proposes to expand the knowledge of pre-trained diffusion models to allow them to understand various object parts, enabling them to perform fine-grained edits, and achieves this by learning special textual tokens that correspond to different object parts through an efficient token optimization process.
- EditClip: Representation Learning for Image Editing7
Experiments show that EditCLIP aligns more closely with human judgments than existing CLIP-based metrics, providing a reliable measure of edit quality and structural preservation.
- Ellipse Detection for Visual Cyclists Analysis “In the Wild”7
This paper investigates the problem of ellipse detection for visual cyclists analysis in the wild with the introduction of a new challenging annotated dataset for bicycle wheels, collected in real-world urban environment and develops a method that combines reliable arcs selection and grouping strategies for ellipSE detection.
- 7
- Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation6
This work introduces an automated pipeline that constructs image pairs with annotated semantic and visual correspondences based on existing subject-driven image generation datasets, and proposes a new metric, Visual Semantic Matching (VSM), that quantifies visual inconsistencies in subject-driven image generation.
- 6
- LatentMan : Generating Consistent Animated Characters using Image Diffusion Models6
The proposed approach outperforms existing zero-shot T2V approaches in generating videos of animated characters in terms of pixel-wise consistency and user preference and introduces LATENTMAN that leverages existing text-based motion diffusion models to generate diverse continuous motions to guide the T2I model.
- Hinge-Wasserstein: Estimating Multimodal Aleatoric Uncertainty in Regression Tasks6
This work proposes hinge-Wasserstein – a simple improvement of the Wasserstein loss that reduces the penalty for weak secondary modes during training, which enables prediction of complex distributions with multiple modes, and allows training on datasets where full ground truth distributions are not available.
- ZeroKey: Point-Level Reasoning and Zero-Shot 3D Keypoint Detection from Large Language Models3
It is demonstrated, for the first time, that pixel-level annotations used to train recent MLLMs can be exploited for both extracting and naming salient keypoints on 3D models without any ground truth labels or supervision.
- Distractor-Aware Video Object Segmentation3
This work proposes a one-versus-many scheme to address the situation by separating distractors into their own class, which sets a new state-of-the-art on the DAVIS 2017 val dataset, and improves over the baseline on the DAVIS 2017 test-dev benchmark by 4.6 percentage points.
- CounterCount: A Diagnostic Framework for Counting Bias in Vision Language Models1
A unified inference-time attention modulation strategy is introduced that reweights selected visual tokens, improving counterfactual counting accuracy by up to 8% across multiple VLMs and provides diagnostic insights for designing future VLMs.
- 1
- 1
- Skill-Aligned Annotation for Reliable Evaluation in Text-to-Image Generation–
This work revisits T2I evaluation through the lens of skill-aligned annotation, where annotation strategies reflect the underlying characteristics of each evaluation skill, and systematically compares skill-aligned annotation against uniform baselines and shows that it produces more consistent evaluation signals.
- –
- –
- Telco-GAIA: Bilingual Benchmark for Agents in Telecom Domain–
This work introduces Telco-GAIA, a bilingual, multi-modal benchmark for evaluating tool-using agents on the data of a real-world telecommunications operator, and offers a rigorous, reproducible testbed for enterprise agents and a template for constructing closed-domain benchmarks.
- SoccerLens: Grounded Soccer Video Understanding Beyond Accuracy–
This work introduces SoccerLens, a benchmark for grounded soccer video understanding, and extends the attribution method of Chefer to jointly model spatial and temporal attention, and introduces evaluation metrics that measure whether model attention aligns with annotated cues or drifts toward spurious regions.
- NearID: Identity Representation Learning via Near-Identity Distractors–
This work introduces the first principled framework to address this vulnerability using Near-identity (NearID) distractors, where semantically similar but distinct instances are placed on the exact same background as a reference image, eliminating contextual shortcuts and isolating identity as the sole discriminative signal.
- HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models–
This work proposes HyperSafe, a framework that restores safety behavior by generating a model-specific Safe Side Network (SSN) for each fine-tuned checkpoint by using layer-wise activation fingerprints to capture how fine-tuning changes the model's inner representations.
- –
- –
- AvatarMMC: 3D Head Avatar Generation and Editing with Multi-Modal Conditioning–
This approach is the first to introduce multi-modal conditioning to 3D avatar generation and editing with multi-modal conditioning based on a 3D Generative Adversarial Network (GAN) and a Latent Diffusion Model (LDM).
- Uncertainty-Aware Convolutional Neural Networks for Vision Tasks on Sparse Data–
A novel variation of CNNs denoted as the Normalized Convolutional Neural Networks that can directly handle sparse data very efficiently is proposed that is structure-aware while being light-weight and derived a probabilistic framework for the normalized convolutional neural networks.
- –
- –
- Scale-Adaptive Object Tracking with Diverse Ensembles–
Experimental results obtained with publicly-available visual tracking datasets demonstrate that the proposed tracker provides robust tracking in case of significant scale variations with more accurate overlap and less visual drift.
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 2026-10-14. 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.