Recognition Using Visual Phrases CVPR 2011 Best Student Paper
Outline Introduction Related Works Approach Results Discussion Phrasal Recognition Decoding Multiple Detections Results Discussion
Introduction
Introduction Visual Phrases Traditional approach Detect objects (person, dog, horse…) Relation between objects NMS(non-maximum suppression) PASCAL other Disadvantage
Introduction
Introduction Contributions Introducing visual phrases as categories for recognition Introducing a novel dataset for phrasal recognition The state of the art methods of modeling interactions A decoding algorithm Performance results in multi-class object recognition
Related Work Object Recognition Deformable templates [IEEE2001,CVPR1998] Part base model [CVPR2005,CVPR2003] Detectors Deformable based model [IEEE2010]
Related Work Object Interactions left, right, top, down Focus on relation [ECCV2008] Person with object [CVPR 2010] Objects [ECCV2010] Relation of objects [ICCV2010] left, right, top, down label weight, confidence
Related Work Scene understanding Represent scenes as with global features that take into account general information about images [Vision2001,CVPR2006] Cluster [ECCV2008]
Related Work Machine translation Statistical translation methods [Press2010] Translation model Language model A decoding algorithm Output: a query sentence Allow multiple to multiple translation
Phrasal Recognition Phrasal Recognition Dataset select 8 obj. class (Pascal VOC 2008) person, bike, car, dog, horse, bottle, sofa, chair A list of 17 visual phrases + background class Dog jumping ,horse jumping, person riding horse…
Phrasal Recognition
Phrasal Recognition Datasets The complexity of Visual Phrases crease 2769 images (822 negative image) 120 examples, average of each classes 5067 bounding boxes(1796 phrases,3271 objects) The complexity of Visual Phrases crease The number of training example decrease
Phrasal Recognition Appearance models Deformation part model 17 phrases in our dataset using provided bounding boxes 8 categories from Pascal are used as models for objects
Decoding Multiple Detections NMS decoding Perfect detectors with excellent tightly tuned models Natural decoding strategy better than NMS on interaction Greedily search the space of labels Well designed feature (nearby) All detector responses Final outcome Decoding
Decoding Multiple Detections Decoding process We compare our decoding algorithm with that of [2] on our phrase dataset Step1: construct the feature Step2: running algorithm to learn a set of weights that rescore the confidences of the bounding boxes based on interactions Step3: We again rescore until optimal
Discriminative models for multi-class object layout
Decoding Multiple Detections : a bounding box in an image An image is represented as a collection of overlapping Bounding boxes X = { : i=1….M},M is the total num of bounding box K is different categories 1 , 1 1 is the score of image X with Y is the set of weights that corresponds to the class of the bounding box
Decoding Multiple Detections Representation Image = bounding boxes Confidence Overlap Size ratio Relation Above, Below, overlapping Window, category, spatial bins Representation has K*3*3+1 dimensions
Decoding Multiple Detections Inference assume bounding boxes are independent given their features 1
Decoding Multiple Detections Learning A form of max margin structure learning 1
Decoding Multiple Detections 1 our inner maximization is exact and very fast. We solve this optimization problem by subgradient descent method as follows.
Result Single category detection deformable part models for 17 visual phrase the trained models from for objects Use PASCAL dataset : 50 positive and 150 negative examples Show Precision-Recall (PR) curves Trained these detectors with at most 50 positive examples
Result
Result
Result
Result
Result Decoding 0.319 0.313 0.308 0.495 0.493 0.491 Paper decoding *[2] NMS Overall AP 0.319 0.313 0.308 Mean per class AP 0.495 0.493 0.491 [2] C. F. C. Desai, D. Ramanan. Discriminative models for multi-class object layout. In ICCV, 2010.
Result
Result
Discussion Future Work Introduce visual phrases, phrasal recognition dataset A coding algorithm The dimensionality of our features grows with the number of categories Future Work the relations between attributes and objects parts and objects visual phrases and scenes objects and visual phrases mirror one another
Discussion Experience Low complexity Use less data to detection Features grows with the number of categories (exponential 2n) But we don’t need to consider all of the categories when we model the interactions Building long enough phrase tables is still a challenge