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.
Eva-02: A visual representation for neon genesis.Image and Vision Computing, 149:105171,
6 Pith papers cite this work. Polarity classification is still indexing.
representative citing papers
HERA is a select-regularize-calibrate framework adapting frozen vision foundation models for cross-domain few-shot semantic segmentation via hierarchical layer selection with ETR, prior-guided regularization, and pixelwise adaptive calibration, reporting over 4.1 mIoU gains.
SToRe3D delivers up to 3x faster inference for multi-view 3D object detection in ViTs by selecting relevant 2D tokens and 3D queries via mutual relevance heads with only marginal accuracy loss.
MultiModalPFN extends TabPFN with modality projectors, a multi-head gated MLP, and cross-attention pooler to unify tabular and non-tabular inputs, outperforming prior methods on medical and general multimodal datasets.
GeoBridge introduces a semantic-anchor mechanism using text to bridge multi-view image features for bidirectional cross-view and language-to-image geo-localization, supported by the new GeoLoc dataset of over 50,000 aligned pairs.
SemLT3D introduces semantic-guided expert distillation with a language MoE module and CLIP projection to enrich features for long-tailed classes in camera-only 3D detection.
citing papers explorer
-
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.
-
Selective, Regularized, and Calibrated: Harnessing Vision Foundation Models for Cross-Domain Few-Shot Semantic Segmentation
HERA is a select-regularize-calibrate framework adapting frozen vision foundation models for cross-domain few-shot semantic segmentation via hierarchical layer selection with ETR, prior-guided regularization, and pixelwise adaptive calibration, reporting over 4.1 mIoU gains.
-
SToRe3D: Sparse Token Relevance in ViTs for Efficient Multi-View 3D Object Detection
SToRe3D delivers up to 3x faster inference for multi-view 3D object detection in ViTs by selecting relevant 2D tokens and 3D queries via mutual relevance heads with only marginal accuracy loss.
-
MultiModalPFN: Extending Prior-Data Fitted Networks for Multimodal Tabular Learning
MultiModalPFN extends TabPFN with modality projectors, a multi-head gated MLP, and cross-attention pooler to unify tabular and non-tabular inputs, outperforming prior methods on medical and general multimodal datasets.
-
GeoBridge: A Semantic-Anchored Multi-View Foundation Model Bridging Images and Text for Geo-Localization
GeoBridge introduces a semantic-anchor mechanism using text to bridge multi-view image features for bidirectional cross-view and language-to-image geo-localization, supported by the new GeoLoc dataset of over 50,000 aligned pairs.
-
SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detection
SemLT3D introduces semantic-guided expert distillation with a language MoE module and CLIP projection to enrich features for long-tailed classes in camera-only 3D detection.