Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks48 from public data
- Transformer-Based Visual Segmentation: A Survey342
This survey provides a thorough overview of transformer-based visual segmentation, summarizing recent advancements and presents a meta-architecture that unifies all recent transformer-based approaches.
- Seesaw Loss for Long-Tailed Instance Segmentation314
This work proposes Seesaw Loss to dynamically re-balance gradients of positive and negative samples for each category, with two complementary factors, i.e., mitigation factor and compensation factor, which obtains significant gains over Cross-Entropy Loss and achieves state-of-the-art performance on LVIS dataset without bells and whistles.
- Robust Multi-Modality Multi-Object Tracking240
This study designs a generic sensor-agnostic multi-modality MOT framework (mmMOT), where each modality is capable of performing its role independently to preserve reliability, and could further improving its accuracy through a novel multi- modality fusion module.
- EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI206
This work introduces EmbodiedScan, a multi-modal, ego-centric 3D perception dataset and benchmark for holistic 3D scene understanding, and a baseline framework named Embodied Perceptron, capable of processing an arbitrary number of multi-modal inputs and demonstrating remarkable 3D perception capabilities.
- Aligning Bag of Regions for Open-Vocabulary Object Detection200
This work proposes to align the embedding of bag of regions beyond individual regions as a bag, and surpasses the previous best results by 4.6 box AP50 and 2.8 mask AP on novel categories of open-vocabulary COCO and LVIS benchmarks, respectively.
- Side-Aware Boundary Localization for More Precise Object Detection167
This paper proposes an alternative approach, named as Side-Aware Boundary Localization (SABL), where each side of the bounding box is respectively localized with a dedicated network branch, to tackle the difficulty of precise localization in the presence of displacements with large variance.
- CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction159
An in-depth analysis of the region-language alignment in CLIP models is embarked on, which proposes an approach named CLIPSelf, which adapts the image-level recognition ability of CLIP ViT to local image regions without needing any region-text pairs.
- Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation125
Video K-Net is presented, a simple, strong, and unified framework for fully end-to-end video panoptic seg-mentation that achieves state-of-the-art videoPanoptic segmentation results on Citscapes-VPS and KITTI-STEP without bells and whistles and can serve as a new flexible baseline in video segmentation.
- Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving87
LaserMix++ is introduced, an evolved framework that integrates laser beam manipulations from disparate LiDAR scans and incorporates LiDAR-camera correspondences and incorporates LiDAR-camera correspondences to further assist data-efficient learning and markedly outperforms fully supervised alternatives.
- MindSearch: Mimicking Human Minds Elicits Deep AI Searcher83
MindSearch is introduced to mimic the human minds in web information seeking and integration, which can be instantiated by a simple yet effective LLM-based multi-agent framework, and demonstrates significant improvement in the response quality in terms of depth and breadth.
- Harmonizing Visual Representations for Unified Multimodal Understanding and Generation82
Harmon is presented, a unified autoregres-sive framework that harmonizes understanding and generation tasks with a shared MAR encoder and achieves state-of-the-art image generation results on the GenEval, MJHQ30K and WISE benchmarks while matching the performance of methods with dedicated semantic encoders on image understanding benchmarks.
- Benchmarking and Improving Bird’s Eye View Perception Robustness in Autonomous Driving66
This study presents RoboBEV, an extensive benchmark suite designed to evaluate the resilience of BEV algorithms, and designs an effective robustness enhancement strategy based on the CLIP model.
- 51
- OV-PARTS: Towards Open-Vocabulary Part Segmentation49
An Open-Vocabulary Part Segmentation (OV-PARTS) benchmark, providing insights into analogical reasoning, open granularity and few-shot adapting abilities of models, and two prevailing paradigms of existing object-level OVSS methods for OV- PARTS are analyzed and adapted.
- MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training42
The Masked Voxel Jigsaw and Reconstruction (MV-JAR) method for LiDAR-based self-supervised pre-training and a carefully designed data-efficient 3D object detection benchmark on the Waymo dataset is introduced.
- Position-Guided Point Cloud Panoptic Segmentation Transformer40
This work designs a robust Mixed-parameterized Positional Embedding to guide the segmentation process in LiDAR-based point cloud segmentation and outperforms previous state-of-the-art methods by 2.7% and 1.2% PQ on SemanticKITTI and nuScenes datasets, respectively.
- 38
- MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbones37
This solution is built upon a simple monocular detector FCOS3D++, pretrained only with object annotations of Waymo, and converts multi-view features to a 3D grid space to detect 3D objects thereon, and achieves 49.75% mAPL with a single model and wins 2nd place in the WOD challenge.
- CLIM: Contrastive Language-Image Mosaic for Region Representation35
This paper proposes a novel approach called Contrastive Language-Image Mosaic (CLIM), which leverages large-scale image-text pairs effectively for aligning region and text representations and can effectively enhance the region representation of vision-language models, thus providing stronger backbones for open-vocabulary object detectors.
- Object2Scene: Putting Objects in Context for Open-Vocabulary 3D Detection32
Object2Scene is proposed, the first approach that leverages large-scale large-vocabulary 3D object datasets to augment existing 3D scene datasets for open- Vocabulary 3d object detection and a cross-domain category-level contrastive learning approach to mitigate the domain gap between 3D objects from different datasets.
- 29
- The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition28
This challenge has set a new benchmark in the field, providing a rich repository of techniques expected to guide future research in this field, and introduced a range of innovative approaches including advanced data augmentation, multi-sensor fusion, self-supervised learning for error correction, and new algorithmic strategies to enhance sensor robustness.
- 25
- Mixed Pseudo Labels for Semi-Supervised Object Detection20
Mixed Pseudo Labels (MixPL) is proposed, consisting of Mixup and Mosaic for pseudo-labeled data, to mitigate the negative impact of missed detections and balance the model's learning across different object scales.
- LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving19
LargeAD, a versatile and scalable framework designed for large-scale 3D pretraining across diverse real-world driving datasets, leverages VFMs to extract semantically rich superpixels from 2D images, which are aligned with LiDAR point clouds to generate high-quality contrastive samples, and introduces several key innovations.
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.