Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks334 from public data
- Deep High-Resolution Representation Learning for Visual Recognition5,145
The superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, is shown, suggesting that the HRNet is a stronger backbone for computer vision problems.
- CCNet: Criss-Cross Attention for Semantic Segmentation3,111
For each pixel, a novel criss-cross attention module in CCNet harvests the contextual information of all the pixels on its criss-cross path by taking a further recurrent operation, each pixel can finally capture the full-image dependencies from all pixels.
- ByteTrack: Multi-object Tracking by Associating Every Detection Box2,841
A simple, effective and generic association method, tracking by associating almost every detection box instead of only the high score ones, named ByteTrack, which achieves state-of-the-art performance on MOT20, HiEve and BDD100K tracking benchmarks.
- Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model2,242
This paper proposes a new generic vision backbone with bidirectional Mamba blocks (Vim), which marks the image sequences with position embeddings and compresses the visual representation with bidirectional state space models and has great potential to be the next-generation backbone for vision foundation models.
- 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering1,670
This work proposes 4D Gaussian Splatting (4D-GS) as a holistic representation for dynamic scenes rather than applying 3D-GS for each individual frame, and achieves real-time rendering under high resolutions, 82 FPS at an 800x800 resolution on an RTX 3090 GPU while maintaining comparable or better quality than previous state- of-the-art methods.
- YOLO-World: Real-Time Open-Vocabulary Object Detection1,134
YOLO-World is introduced, an innovative approach that enhances YOLO with open-vocabulary detection capabilities through vision-language modeling and pre-training on large-scale datasets and proposes a new Re-parameterizable Vision-Language Path Aggregation Network (RepVL-PAN) and region-text contrastive loss to facilitate the interaction between visual and linguistic information.
- EVA: Exploring the Limits of Masked Visual Representation Learning at Scale1,054
Initializing the vision tower of a giant CLIP from EVA can greatly stabilize the training and outperform the training from scratch counterpart with much fewer samples and less compute, providing a new direction for scaling up and accelerating the costly training of multi-modal foundation models.
- Mask Scoring R-CNN1,049
This paper proposes Mask Scoring R-CNN which contains a network block to learn the quality of the predicted instance masks and calibrates the misalignment between mask quality and mask score, and improves instance segmentation performance by prioritizing more accurate mask predictions during COCO AP evaluation.
- TextBoxes: A Fast Text Detector with a Single Deep Neural Network955
An end-to-end trainable fast scene text detector, named TextBoxes, which detects scene text with both high accuracy and efficiency in a single network forward pass, involving no post-process except for a standard non-maximum suppression.
- 905
- VAD: Vectorized Scene Representation for Efficient Autonomous Driving866
VAD, an end-to-end vectorized paradigm for autonomous driving, which models the driving scene as a fully vectorized representation, achieves state-of-the-art end-to-end planning performance on the nuScenes dataset, outperforming the previous best method by a large margin.
- Robust Scene Text Recognition with Automatic Rectification693
RARE (Robust text recognizer with Automatic REctification), a recognition model that is robust to irregular text, which is end-to-end trainable, requiring only images and associated text labels, making it convenient to train and deploy the model in practical systems.
- 615
- EVA-02: A visual representation for neon genesis608
EVA-02, a next-generation Transformer-based visual representation pre-trained to reconstruct strong and robust language-aligned vision features via masked image modeling, is launched, demonstrating superior performance compared to prior state-of-the-art approaches across various representative vision tasks, while utilizing significantly fewer parameters and compute budgets.
- 595
- 567
- Revisiting multiple instance neural networks533
This article revisit Multiple Instance Neural Networks (MINNs) that the neural networks aim at solving the MIL problems and proposes a new type of MINN to learn bag representations, which is different from the existing MINNs that focus on estimating instance label.
- YOLOP: You Only Look Once for Panoptic Driving Perception495
To the best knowledge, this is the first work that can process these three visual perception tasks simultaneously in real-time on an embedded device Jetson TX2(23 FPS), and maintain excellent accuracy.
- Multiple Instance Detection Network with Online Instance Classifier Refinement494
This work formulate weakly supervised object detection as a Multiple Instance Learning (MIL) problem, where instance classifiers (object detectors) are put into the network as hidden nodes and instance labels inferred from weak supervision are propagated to their spatially overlapped instances to refine instance classifier online.
- Fast Dynamic Radiance Fields with Time-Aware Neural Voxels492
This framework significantly accelerates the optimization of dynamic radiance fields while maintaining high rendering quality and completes training with only 8 minutes and 8-MB storage cost while showing similar or even better rendering performance than previous dynamic NeRF methods.
- MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction454
A unified permutation-equivalent modeling approach is proposed, i.e., modeling map element as a point set with a group of equivalent permutations, which accurately describes the shape of map element and stabilizes the learning process.
- DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving439
A novel truncated diffusion policy is proposed that incorporates prior multi-mode anchors and truncates the diffusion schedule, enabling the model to learn denoising from anchored Gaussian distribution to the multi-mode driving action distribution.
- Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-Identification410
A novel deep network called Mancs is proposed that solves the person re-identification problem from the following aspects: fully utilizing the attention mechanism for the person misalignment problem and properly sampling for the ranking loss to obtain more stable person representation.
- PCL: Proposal Cluster Learning for Weakly Supervised Object Detection408
This paper first shows that instances can be assigned object or background labels directly based on proposal clusters for instance classifier refinement, and then shows that treating each cluster as a small new bag yields fewer ambiguities than the directly assigning label method.
- Unsupervised domain adaptive re-identification: Theory and practice376
A novel self-training scheme for unsupervised domain adaptive re-identification (re-ID) that iteratively makes guesses for unlabeled target data based on an encoder and trains the encoder based on the guessed labels.
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.