Skip to search formSkip to main contentSkip to account menu

DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

DeCAF, an open-source implementation of deep convolutional activation features, along with all associated network parameters, are released to enable vision researchers to be able to conduct experimentation with deep representations across a range of visual concept learning paradigms.
View PDF on arXiv (opens in a new tab)

Compact Bilinear Pooling

Two compact bilinear representations are proposed with the same discriminative power as the full bil inear representation but with only a few thousand dimensions allowing back-propagation of classification errors enabling an end-to-end optimization of the visual recognition system.
View on IEEE (opens in a new tab)

Part-Based R-CNNs for Fine-Grained Category Detection

This work proposes a model for fine-grained categorization that overcomes limitations by leveraging deep convolutional features computed on bottom-up region proposals, and learns whole-object and part detectors, enforces learned geometric constraints between them, and predicts a fine- grained category from a pose-normalized representation.
View PDF on arXiv (opens in a new tab)

PANDA: Pose Aligned Networks for Deep Attribute Modeling

A new method which combines part-based models and deep learning by training pose-normalized CNNs for inferring human attributes from images of people under large variation of viewpoint, pose, appearance, articulation and occlusion is proposed.
View on IEEE (opens in a new tab)

Beyond frontal faces: Improving Person Recognition using multiple cues

The Pose Invariant PErson Recognition (PIPER) method is proposed, which accumulates the cues of poselet-level person recognizers trained by deep convolutional networks to discount for the pose variations, combined with a face recognizer and a global recognizer.
View on IEEE (opens in a new tab)

Visual Attention Model for Name Tagging in Multimodal Social Media

This paper creates two new multimodal datasets and proposes a novel model architecture based on Visual Attention that not only provides deeper visual understanding on the decisions of the model, but also significantly outperforms other state-of-the-art baseline methods for this task.
View on ACL (opens in a new tab)

Multi-view to Novel View: Synthesizing Novel Views With Self-learned Confidence

This paper proposes an end-to-end trainable framework that learns to exploit multiple viewpoints to synthesize a novel view without any 3D supervision, and introduces a self-learned confidence aggregation mechanism.
View via Publisher (opens in a new tab)

Do Convnets Learn Correspondence?

Evidence is presented that convnet features localize at a much finer scale than their receptive field sizes, that they can be used to perform intraclass aligment as well as conventional hand-engineered features, and that they outperform conventional features in keypoint prediction on objects from PASCAL VOC 2011.
View PDF on arXiv (opens in a new tab)

Birdlets: Subordinate categorization using volumetric primitives and pose-normalized appearance

An approach for subordinate categorization in vision is developed, focusing on an avian domain due to the fine-grained structure of the category taxonomy for this domain, and a pose-normalized appearance model based on a volumetric poselet scheme is explored.
View on IEEE (opens in a new tab)

Deformable Part Descriptors for Fine-Grained Recognition and Attribute Prediction

This paper proposes two pose-normalized descriptors based on computationally-efficient deformable part models based on strongly-supervised DPM parts, which enable pooling across pose and viewpoint, in turn facilitating tasks such as fine-grained recognition and attribute prediction.
View on IEEE (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)