AI Paper Atlas

Research map / Detection and segmentation / CNN features

BIND: Binary Integrated Net Descriptors for Texture-Less Object Recognition

Jacob Chan, Jimmy Addison Lee, Qian Kemao

CVPR 2017 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 21 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use multi-layer binary nets to encode object edges and internal homogeneous regionsBIND · MODrecognition performanceImproved
Use multi-layer binary nets to encode object edges and internal homogeneous regionsBIND · D-Texturelessrecognition performanceImproved
Use multi-layer binary nets to encode object edges and internal homogeneous regionsBIND · CMU-KO8true positive rateImproved
Use polarity-invariant angle primitives and two-way matchingBIND · MODrecognition performanceImproved
Use high-resolution regional nets to encode homogeneous space and edgesBIND · D-Texturelessrecognition performanceImproved
Use maximal linelet fragmentationBIND · BIND experimentsrecognition speedHurt
Use maximal linelet fragmentationBIND · BIND experimentsrecognition performanceNo clear effect
Use byte-indexed storage that stores only informative bytesBIND · BIND experimentsdescriptor storage: about 50%Improved
Use byte-indexed storage that stores only informative bytesBIND · BIND experimentsmatch speedImproved
Use BIND’s precise linelet and description processBIND · BIND experimentsruntime speedup versus BORDER: 2.2 times fasterImproved
Apply BIND’s texture-less-specific 3-layer bit combination to low-homogeneity objectsBIND · low-homogeneity objectsrecognition performanceHurt

Later papers that compared with this method

1 later accepted paper reports BIND as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy