Presents the CANSURF dataset for surface-level aluminum can detection from ASV viewpoints and shows that training YOLOv11 on it yields a 12x performance boost over generic datasets along with stable tracking results.
hub Mixed citations
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
Mixed citation behavior. Most common role is background (54%).
85
Pith papers citing it
Background
54% of classified citations
abstract
In this paper, we present an open-set object detector, called Grounding DINO, by marrying Transformer-based detector DINO with grounded pre-training, which can detect arbitrary objects with human inputs such as category names or referring expressions. The key solution of open-set object detection is introducing language to a closed-set detector for open-set concept generalization. To effectively fuse language and vision modalities, we conceptually divide a closed-set detector into three phases and propose a tight fusion solution, which includes a feature enhancer, a language-guided query selection, and a cross-modality decoder for cross-modality fusion. While previous works mainly evaluate open-set object detection on novel categories, we propose to also perform evaluations on referring expression comprehension for objects specified with attributes. Grounding DINO performs remarkably well on all three settings, including benchmarks on COCO, LVIS, ODinW, and RefCOCO/+/g. Grounding DINO achieves a $52.5$ AP on the COCO detection zero-shot transfer benchmark, i.e., without any training data from COCO. It sets a new record on the ODinW zero-shot benchmark with a mean $26.1$ AP. Code will be available at \url{https://github.com/IDEA-Research/GroundingDINO}.
hub tools
citation-role summary
background 12
method 11
dataset 1
citation-polarity summary
claims ledger
- abstract In this paper, we present an open-set object detector, called Grounding DINO, by marrying Transformer-based detector DINO with grounded pre-training, which can detect arbitrary objects with human inputs such as category names or referring expressions. The key solution of open-set object detection is introducing language to a closed-set detector for open-set concept generalization. To effectively fuse language and vision modalities, we conceptually divide a closed-set detector into three phases and propose a tight fusion solution, which includes a feature enhancer, a language-guided query selec
co-cited works
representative citing papers
VISTA is the first large-scale interaction-aware benchmark that decomposes videos into entities, actions, and relations to diagnose spatio-temporal biases in vision-language models.
CoMoGen generates controllable interactive video from mask sequences and images by encoding masks into MMDiT via MaskAdapter and LoRA on motion layers, claiming SOTA motion fidelity.
GesVLA encodes gesture features directly into the latent space of VLA models using a dual-VLM architecture and a rendering-based data pipeline, yielding improved target grounding in real robotic tasks.
Foundation models yield less human-interpretable features than supervised vision transformers, with interpretability tied to activation locality and coarse semantic alignment rather than task performance.
VASA is a vision-guided agent for open ad-hoc segmentation that creates and validates masks through planning, tool use, and error recovery, outperforming baselines on the new PARS benchmark and RefCOCOm.
CosFlyTrack provides 12,000 expert UAV trajectories with aligned RGB, depth, segmentation, pose, target state, and bilingual instructions to train visual tracking agents, yielding 53-69 point gains in success rate after fine-tuning.
Seg-Agent performs language-guided segmentation without training by using Set-of-Mark visual prompts to enable explicit multimodal chain-of-reasoning in three stages: generation, selection, and refinement.
Urban-ImageNet is a 2-million-image multi-modal dataset with HUSIC 10-class taxonomy enabling benchmarks for urban scene classification, cross-modal retrieval, and instance segmentation.
LAGO achieves state-of-the-art zero-shot performance with fewer image regions by using class-agnostic object discovery followed by confidence-controlled language-guided refinement and dual-channel aggregation.
Symmetric Nucleus Subsampling and Expert Embedding Engine reduce modality gaps in multimodal embeddings by over 90% and outperform baselines in data curation for downstream models.
PanDA is the first UDA method for multimodal 3D panoptic segmentation that improves robustness to single-modality degradation and pseudo-label completeness via asymmetric augmentation and dual-expert refinement.
SPRITE converts static game UI screenshots into editable engine-ready assets by using VLMs to parse complex layouts into a YAML intermediate representation.
DOMINO dataset and PUMA architecture enable better dynamic robotic manipulation by incorporating motion history, delivering 6.3% higher success rates than prior VLA models.
ProcObject-10K is the first benchmark for object-centric procedural reasoning in videos that exposes a large gap where models answer questions plausibly but fail to ground their answers in the correct video segments.
VACE unifies reference-to-video generation, video-to-video editing, and masked video-to-video editing in one Diffusion Transformer framework using a Video Condition Unit for inputs and a Context Adapter for task injection.
VideoRepair detects text-video misalignments via MLLM-generated questions and performs localized, region-preserving refinement to improve alignment in existing T2V diffusion models.
RoboDreamer factorizes video generation using language primitives to achieve compositional generalization in robot world models, outperforming monolithic baselines on unseen goals in RT-X.
Qwen3-VL-Seg decodes MLLM bounding boxes into pixel-level referring segmentation via a lightweight box-guided mask decoder, new SA1B-ORS training data, and ORS-Bench evaluation, showing strong open-world performance.
A new benchmark converts video clips into shared grounded event records and tests models across physics, semantic, and control prompts under original, shuffled, ablated, and masked conditions, finding selective robustness and weak spatial performance.
Seg2Change adapts open-vocabulary segmentation models to open-vocabulary change detection via a category-agnostic change head and new dataset CA-CDD, delivering +9.52 IoU on WHU-CD and +5.50 mIoU on SECOND.
WildDet3D is a promptable 3D detector paired with a new 1M-image dataset across 13.5K categories that sets SOTA on open-world and zero-shot 3D detection benchmarks.
KITE is a training-free method that uses keyframe-indexed tokenized evidence including BEV schematics to enhance VLM performance on robot failure detection, identification, localization, explanation, and correction.
LLaVA is trained on GPT-4 generated visual instruction data to achieve 85.1% relative performance to GPT-4 on synthetic multimodal tasks and 92.53% accuracy on Science QA.
citing papers explorer
-
CANSURF: An ASV-View Can Dataset and Benchmark for Detection and Tracking of Surface-Level Debris
Presents the CANSURF dataset for surface-level aluminum can detection from ASV viewpoints and shows that training YOLOv11 on it yields a 12x performance boost over generic datasets along with stable tracking results.
-
VISTA: Video Interaction Spatio-Temporal Analysis Benchmark
VISTA is the first large-scale interaction-aware benchmark that decomposes videos into entities, actions, and relations to diagnose spatio-temporal biases in vision-language models.
-
CoMoGen: COntrollable MOtion Dynamics and Interactions with Mask-Guided Video GENeration
CoMoGen generates controllable interactive video from mask sequences and images by encoding masks into MMDiT via MaskAdapter and LoRA on motion layers, claiming SOTA motion fidelity.
-
GesVLA: Gesture-Aware Vision-Language-Action Model Embedded Representations
GesVLA encodes gesture features directly into the latent space of VLA models using a dual-VLM architecture and a rendering-based data pipeline, yielding improved target grounding in real robotic tasks.
-
Capability $\neq$ Interpretability: Human Interpretability of Vision Foundation Models
Foundation models yield less human-interpretable features than supervised vision transformers, with interpretability tied to activation locality and coarse semantic alignment rather than task performance.
-
Vision Harnessing Agent for Open Ad-hoc Segmentation
VASA is a vision-guided agent for open ad-hoc segmentation that creates and validates masks through planning, tool use, and error recovery, outperforming baselines on the new PARS benchmark and RefCOCOm.
-
CosFly-Track: A Large-Scale Multi-Modal Dataset for UAV Visual Tracking via Multi-Constraint Trajectory Optimization
CosFlyTrack provides 12,000 expert UAV trajectories with aligned RGB, depth, segmentation, pose, target state, and bilingual instructions to train visual tracking agents, yielding 53-69 point gains in success rate after fine-tuning.
-
Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation
Seg-Agent performs language-guided segmentation without training by using Set-of-Mark visual prompts to enable explicit multimodal chain-of-reasoning in three stages: generation, selection, and refinement.
-
Urban-ImageNet: A Large-Scale Multi-Modal Dataset and Evaluation Framework for Urban Space Perception
Urban-ImageNet is a 2-million-image multi-modal dataset with HUSIC 10-class taxonomy enabling benchmarks for urban scene classification, cross-modal retrieval, and instance segmentation.
-
LAGO: Language-Guided Adaptive Object-Region Focus for Zero-Shot Visual-Text Alignment
LAGO achieves state-of-the-art zero-shot performance with fewer image regions by using class-agnostic object discovery followed by confidence-controlled language-guided refinement and dual-channel aggregation.
-
Multimodal Data Curation Through Ranked Retrieval
Symmetric Nucleus Subsampling and Expert Embedding Engine reduce modality gaps in multimodal embeddings by over 90% and outperform baselines in data curation for downstream models.
-
PanDA: Unsupervised Domain Adaptation for Multimodal 3D Panoptic Segmentation in Autonomous Driving
PanDA is the first UDA method for multimodal 3D panoptic segmentation that improves robustness to single-modality degradation and pseudo-label completeness via asymmetric augmentation and dual-expert refinement.
-
SPRITE: From Static Mockups to Engine-Ready Game UI
SPRITE converts static game UI screenshots into editable engine-ready assets by using VLMs to parse complex layouts into a YAML intermediate representation.
-
Towards Generalizable Robotic Manipulation in Dynamic Environments
DOMINO dataset and PUMA architecture enable better dynamic robotic manipulation by incorporating motion history, delivering 6.3% higher success rates than prior VLA models.
-
ProcObject-10K: Benchmarking Object-Centric Procedural Understanding in Instructional Videos
ProcObject-10K is the first benchmark for object-centric procedural reasoning in videos that exposes a large gap where models answer questions plausibly but fail to ground their answers in the correct video segments.
-
VACE: All-in-One Video Creation and Editing
VACE unifies reference-to-video generation, video-to-video editing, and masked video-to-video editing in one Diffusion Transformer framework using a Video Condition Unit for inputs and a Context Adapter for task injection.
-
Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement
VideoRepair detects text-video misalignments via MLLM-generated questions and performs localized, region-preserving refinement to improve alignment in existing T2V diffusion models.
-
RoboDreamer: Learning Compositional World Models for Robot Imagination
RoboDreamer factorizes video generation using language primitives to achieve compositional generalization in robot world models, outperforming monolithic baselines on unseen goals in RT-X.
-
Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding
Qwen3-VL-Seg decodes MLLM bounding boxes into pixel-level referring segmentation via a lightweight box-guided mask decoder, new SA1B-ORS training data, and ORS-Bench evaluation, showing strong open-world performance.
-
Grounding Video Reasoning in Physical Signals
A new benchmark converts video clips into shared grounded event records and tests models across physics, semantic, and control prompts under original, shuffled, ablated, and masked conditions, finding selective robustness and weak spatial performance.
-
Seg2Change: Adapting Open-Vocabulary Semantic Segmentation Model for Remote Sensing Change Detection
Seg2Change adapts open-vocabulary segmentation models to open-vocabulary change detection via a category-agnostic change head and new dataset CA-CDD, delivering +9.52 IoU on WHU-CD and +5.50 mIoU on SECOND.
-
WildDet3D: Scaling Promptable 3D Detection in the Wild
WildDet3D is a promptable 3D detector paired with a new 1M-image dataset across 13.5K categories that sets SOTA on open-world and zero-shot 3D detection benchmarks.
-
KITE: Keyframe-Indexed Tokenized Evidence for VLM-Based Robot Failure Analysis
KITE is a training-free method that uses keyframe-indexed tokenized evidence including BEV schematics to enhance VLM performance on robot failure detection, identification, localization, explanation, and correction.
-
Visual Instruction Tuning
LLaVA is trained on GPT-4 generated visual instruction data to achieve 85.1% relative performance to GPT-4 on synthetic multimodal tasks and 92.53% accuracy on Science QA.
-
Action with Visual Primitives
AVP architecture has VLM emit visual-primitive tokens to condition flow-matching action expert, yielding 27.61% higher success rate than pi_0.5 on real-robot pick-and-place tasks.
-
Beyond Pixels: Learning Invariant Rewards for Real-World Robotics From a Few Demonstrations
A framework learns invariant symbolic reward functions from few demonstrations that generalize zero-shot to variations in robotic manipulation tasks.
-
UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation
UniVL unifies vision and language into one mask-rendered input processed by an OCR backbone to condition diffusion models for spatially grounded image generation without a standalone text encoder.
-
ReactiveGWM: Steering NPC in Reactive Game World Models
ReactiveGWM introduces a decoupled diffusion architecture for player-NPC interactions that learns game-agnostic response logic for zero-shot strategy transfer across games.
-
GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning
GS-Playground delivers a high-throughput photorealistic simulator for vision-informed robot learning via parallel physics integrated with batch 3D Gaussian Splatting at 10^4 FPS and an automated Real2Sim workflow for consistent environments.
-
WildLIFT: Lifting monocular drone video to 3D for species-agnostic wildlife monitoring
WildLIFT lifts monocular drone video to 3D for species-agnostic wildlife detection, tracking, and viewpoint analysis by integrating scene geometry with open-vocabulary segmentation.
-
Pi-HOC: Pairwise 3D Human-Object Contact Estimation
Pi-HOC predicts dense 3D semantic contacts for all human-object pairs in an image via instance-aware tokens and an InteractionFormer, achieving higher accuracy and 20x throughput than prior methods.
-
From Local Matches to Global Masks: Template-Guided Instance Detection and Segmentation in Open-World Scenes
L2G-Det detects and segments novel object instances in open scenes by using local template patch matches to generate points that prompt an augmented SAM for global masks.
-
ESPADA: Execution Speedup via Semantics Aware Demonstration Data Downsampling for Imitation Learning
ESPADA uses semantic segmentation from VLMs and LLMs plus DTW to downsample non-critical segments in demonstrations, delivering about 2x faster robot execution in behavior cloning while maintaining task success rates.
-
Think Before You Drive: World Model-Inspired Multimodal Grounding for Autonomous Vehicles
ThinkDeeper introduces a world-model-based reasoning step that predicts future spatial states to improve multimodal visual grounding for autonomous vehicles, achieving top results on Talk2Car and other benchmarks.
-
RADSeg: Unleashing Parameter and Compute Efficient Zero-Shot Open-Vocabulary Segmentation Using Agglomerative Models
RADSeg adapts the RADIO model with targeted enhancements to deliver 6-30% higher mIoU in zero-shot OVSS while using 2.5x fewer parameters and running 3.95x faster than prior large-model combinations.
-
Eevee: Towards Close-up High-resolution Video-based Virtual Try-on
A new dataset with high-fidelity close-up garment images and full/close-up try-on videos plus the VGID metric enables better texture and structure preservation in high-resolution video virtual try-on.
-
SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding
SPEAR-1 combines a 3D-enriched VLM with embodied control to match or exceed existing robotic foundation models using 20 times fewer robot demonstrations.
-
Memory-SAM: Human-Prompt-Free Tongue Segmentation via Retrieval-to-Prompt
Memory-SAM retrieves similar prior cases via DINOv3 features and FAISS to generate point prompts for SAM2, achieving mIoU 0.9863 on 600 tongue images without training or human prompts.
-
Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations
RIGVid shows that filtered AI-generated videos can serve as effective supervision for complex robotic manipulation tasks without any real demonstrations.
-
GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data
GraspVLA shows that pretraining a grasping model on a billion synthetic action frames enables zero-shot open-vocabulary performance and sim-to-real transfer.
-
Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP
Grad-ECLIP produces gradient-based visual and textual explanation heatmaps for CLIP by applying channel and spatial weights to token features instead of relying on sparse self-attention maps.
-
Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks
Uni-NaVid unifies diverse embodied navigation tasks into one video-based vision-language-action model trained on 3.6 million samples from four sub-tasks, achieving state-of-the-art performance on benchmarks and real-world tests.
-
OS-ATLAS: A Foundation Action Model for Generalist GUI Agents
OS-Atlas, trained on the largest open-source cross-platform GUI grounding corpus of 13 million elements, outperforms prior open-source models on six benchmarks across mobile, desktop, and web platforms.
-
Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception
Mobile-Agent is a vision-centric autonomous agent that uses MLLMs to perceive UI elements, plan complex multi-step tasks, and operate mobile apps without relying on XML or system metadata, showing strong results on the introduced Mobile-Eval benchmark.
-
ShareGPT4V: Improving Large Multi-Modal Models with Better Captions
A new 1.2M-caption dataset generated via GPT-4V improves LMMs on MME and MMBench by 222.8/22.0/22.3 and 2.7/1.3/1.5 points respectively when used for supervised fine-tuning.
-
Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual Reasoning
RIS improves MLLM latent visual reasoning by retrieving spatial-semantic evidence, integrating it via attention bottlenecks, and synthesizing it with language transition tokens, yielding gains on V*, HRBench, MMVP, and BLINK benchmarks.
-
Local Intrinsic Dimension Unveils Hallucinations in Diffusion Models
Hallucinations in diffusion models are driven by local intrinsic dimension instabilities on the manifold, which Intrinsic Quenching corrects by deflating it.
-
Approaching human parity in the quality of automated organoid image segmentation
A composite SAM-based method segments organoid images with accuracy matching or approaching inter-observer variability among human annotators.
-
GS4City: Hierarchical Semantic Gaussian Splatting via City-Model Priors
GS4City derives geometry-grounded semantic masks from LoD3 CityGML models via raycasting and fuses them with 2D foundation model outputs to supervise identity encodings on Gaussians, improving coarse and fine semantic segmentation on urban datasets.
-
Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization
VLM-based harmonization of inconsistent annotations across two document layout corpora raises detection F-score from 0.860 to 0.883 and table TEDS from 0.750 to 0.814 while tightening embedding clusters.