Skip to search formSkip to main contentSkip to account menu

No-Frills Human-Object Interaction Detection: Factorization, Layout Encodings, and Training Techniques

We show that for human-object interaction detection a relatively simple factorized model with appearance and layout encodings constructed from pre-trained object detectors outperforms more…
View on IEEE (opens in a new tab)

Contrastive Learning for Weakly Supervised Phrase Grounding

It is shown that phrase grounding can be learned by optimizing word-region attention to maximize a lower bound on mutual information between images and caption words.
View PDF on arXiv (opens in a new tab)

Towards General Purpose Vision Systems

GPV-1 is proposed, a task-agnostic vision-language architecture that can learn and perform tasks that involve receiving an image and producing text and/or bounding boxes, including classification, localization, visual question answering, captioning, and more.
View PDF on arXiv (opens in a new tab)

Completing 3D object shape from one depth image

This work takes an exemplar-based approach: retrieve similar objects in a database of 3D models using view-based matching and transfer the symmetries and surfaces from retrieved models to fully automatically reconstruct a 3D model from any category.
View on IEEE (opens in a new tab)

Visual Semantic Role Labeling for Video Understanding

This work introduces the VidSitu benchmark, a large scale video understanding data source with 29K 10-second movie clips richly annotated with a verb and semantic-roles every 2 seconds, and provides a comprehensive analysis of the dataset in comparison to other publicly available video understanding benchmarks, several illustrative baselines and evaluate a range of standard video recognition models.
View on IEEE (opens in a new tab)

Imagine This! Scripts to Compositions to Videos

This work presents the Composition, Retrieval, and Fusion Network (CRAFT), a model capable of learning knowledge from video-caption data and applying it while generating videos from novel captions, and evaluates CRAFT on semantic fidelity to caption, composition consistency, and visual quality.
View PDF on arXiv (opens in a new tab)

No-Frills Human-Object Interaction Detection: Factorization, Appearance and Layout Encodings, and Training Techniques

We show that with an appropriate factorization, and encodings of layout and appearance constructed from outputs of pretrained object detectors, a relatively simple model outperforms more…
View PDF on arXiv (opens in a new tab)

ViCo: Word Embeddings From Visual Co-Occurrences

This work extracts four types of visual co-occurrences between object and attribute words from large-scale, textually-annotated visual databases like VisualGenome and ImageNet and trains a multi-task log-bilinear model that compactly encodes word ``meanings'' represented by each co- Occurrence type into a single visual word-vector.
View on IEEE (opens in a new tab)

Webly Supervised Concept Expansion for General Purpose Vision Models

This work uses a dataset of 1M+ images spanning 10k+ visual concepts to demonstrate webly-supervised concept expansion for two existing GPVs and proposes a new architecture, GPV-2, that supports a variety of tasks — from vision tasks like classification and localization to vision+language tasks like QA and captioning, to more niche ones like human-object interaction detection.
View PDF on arXiv (opens in a new tab)

Learning Curves for Analysis of Deep Networks

A method is proposed to robustly estimate learning curves, abstract their parameters into error and data-reliance, and evaluate the effectiveness of different parameterizations for a variety of image classification models.
View PDF on arXiv (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)