Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks158 from public data
- 3,013
- Distractor-Aware Siamese Networks for Visual Object Tracking1,530
This paper focuses on learning distractor-aware Siamese networks for accurate and long-term tracking, and extends the proposed approach for long- term tracking by introducing a simple yet effective local-to-global search region strategy.
- 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.
- 458
- OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction423
OccFormer, a dual-path transformer network to effectively process the 3D volume for semantic occupancy prediction, achieves a long-range, dynamic, and efficient encoding of the camera-generated 3D voxel features.
- WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition375
A distributed framework is developed to train face recognition models efficiently without tampering with the performance, and comprehensive baselines are established on a rich-attribute test set under FRUITS-100ms/500ms/1000ms protocol.
- MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer338
MonoViT is a brand-new framework combining the global reasoning enabled by ViT models with the flexibility of self-supervised monocular depth estimation, yielding depth prediction at a higher level of detail and accuracy, allowing MonoViT to achieve state-of-the-art performance on the established KITTI dataset.
- OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception321
In the OpenOccupancy benchmark, the large-scale nuScenes dataset is extended with dense semantic occupancy annotations and the Cascade Occupancy Network (CONet) is proposed to refine the coarse prediction, which relatively enhances the performance by ∼30% than the baseline.
- End-to-End Flow Correlation Tracking with Spatial-Temporal Attention314
The FlowTrack is proposed, which focuses on making use of the rich flow information in consecutive frames to improve the feature representation and the tracking accuracy and is the first work to jointly train flow and tracking task in deep learning framework.
- DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving310
The proposed DriveDreamer is the first world model established from real-world driving scenarios, harnessing the powerful diffusion model to construct a comprehensive representation of the complex environment and introduces a two-stage training pipeline.
- 294
- Attention-Guided Unified Network for Panoptic Segmentation293
The underlying relationship between FG objects and BG contents is revealed, in particular, FG objects provide complementary cues to assist BG understanding, and the Attention-guided Unified Network (AUNet) is named, a unified framework with two branches for FG and BG segmentation simultaneously.
- BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving291
The multi-task BEVerse outperforms existing single-task methods on 3D object detection, semantic map construction, and motion prediction and favors in significantly improved efficiency.
- The Devil Is in the Details: Delving Into Unbiased Data Processing for Human Pose Estimation284
The Unbiased Data Processing (UDP) for human pose estimation can be achieved by combining the two together and not only boosts the performance of existing methods by a large margin but also plays a important role in result reproducing and future exploration.
- CompletionFormer: Depth Completion with Convolutions and Vision Transformers201
A Joint Convolutional Attention and Transformer block (JCAT), which deeply couples the convolutional attention layer and Vision Transformer into one block, as the basic unit to construct the depth completion model in a pyramidal structure, which outperforms state-of-the-art CNNs-based methods on the outdoor KITTI Depth Completion benchmark and indoor NYUv2 dataset.
- CAFE: Learning to Condense Dataset by Aligning Features165
This paper proposes a novel scheme to Condense dataset by Aligning FEatures (CAFE), which explicitly attempts to preserve the real-feature distribution as well as the discriminant power of the resulting synthetic set, lending itself to strong generalization capability to various architectures.
- MVSTER: Epipolar Transformer for Efficient Multi-View Stereo148
MVSTER uses a detachable monocular depth estimator to enhance 2D semantics and uses cross-attention to construct data-dependent 3D associations along epipolar line and is built in a cascade structure, where entropy-regularized optimal transport is leveraged to propagate finer depth estimations in each stage.
- DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation145
DriveDreamer4D is the first to utilize video generation models for improving 4D reconstruction in driving scenarios and significantly enhances generation quality under novel trajectory views, achieving a relative improvement in FID compared to PVG, S3Gaussian, and Deformable-GS.
- DriveWorld: 4D Pre-Trained Scene Understanding via World Models for Autonomous Driving129
This paper proposes a Memory State-Space Model for spatiotemporal modelling, which consists of a Dynamic Memory Bank module for learning temporal-aware latent dynamics to predict future changes and a Static Scene Propagation module for learning spatial-aware latent statics to offer comprehensive scene contexts.
- SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation112
This paper proposes a SurroundDepth method to incorporate the information from multiple surrounding views to predict depth maps across cameras, and adopts the two-frame structure-from-motion to extract scale-aware pseudo depths to pretrain the models.
- 111
- ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration100
ReconDreamer is introduced, which enhances driving scene reconstruction through incremental integration of world model knowledge through incremental integration of world model knowledge and is the first method to effectively render in large maneuvers.
- 100
- WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens98
This work introduces WorldDreamer, a pioneering world model to foster a comprehensive comprehension of general world physics and motions, which significantly enhances the capabilities of video generation and showcases versatility in executing tasks such as text-to-video conversion, image-tovideo synthesis, and video editing.
- End-to-end Video-level Representation Learning for Action Recognition97
This paper builds upon two-stream ConvNets and proposes Deep networks with Temporal Pyramid Pooling (DTPP), an end-to-end video-level representation learning approach, to address problems of partial observation training and single temporal scale modeling in action recognition.
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.