The rise of multi-million-item dataset initiatives has enabled data-hungry machine learning algorithms to reach near-human semantic classification performance at tasks such as visual object and scene recognition. Here we describe the Places Database, a repository of 10 million scene photographs, labeled with scene semantic categories, comprising a large and diverse list of the types of environments encountered in the world. Using the state-of-the-art Convolutional Neural Networks (CNNs), we provide scene classification CNNs (Places-CNNs) as baselines, that significantly outperform the previous approaches. Visualization of the CNNs trained on Places shows that object detectors emerge as an intermediate representation of scene classification. With its high-coverage and high-diversity of exemplars, the Places Database along with the Places-CNNs offer a novel resource to guide future progress on scene recognition problems.

Places: A 10 Million Image Database for Scene Recognition

Top-down visual attention mechanisms have been used extensively in image captioning and visual question answering (VQA) to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning. In this work, we propose a combined bottom-up and top-down attention mechanism that enables attention to be calculated at the level of objects and other salient image regions. This is the natural basis for attention to be considered. Within our approach, the bottom-up mechanism (based on Faster R-CNN) proposes image regions, each with an associated feature vector, while the top-down mechanism determines feature weightings. Applying this approach to image captioning, our results on the MSCOCO test server establish a new state-of-the-art for the task, achieving CIDEr / SPICE / BLEU-4 scores of 117.9, 21.5 and 36.9, respectively. Demonstrating the broad applicability of the method, applying the same approach to VQA we obtain first place in the 2017 VQA Challenge.

/pdf/bottom-up-and-top-down-attention-for-image-captioning-and-2m7gun2469.pdf

Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

The theory of affordances

Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering.

IEEE Transactions on Pattern Analysis and Machine Intelligence

Despite progress in perceptual tasks such as image classification, computers still perform poorly on cognitive tasks such as image description and question answering. Cognition is core to tasks that involve not just recognizing, but reasoning about our visual world. However, models used to tackle the rich content in images for cognitive tasks are still being trained using the same datasets designed for perceptual tasks. To achieve success at cognitive tasks, models need to understand the interactions and relationships between objects in an image. When asked "What vehicle is the person riding?", computers will need to identify the objects in an image as well as the relationships riding(man, carriage) and pulling(horse, carriage) to answer correctly that "the person is riding a horse-drawn carriage." In this paper, we present the Visual Genome dataset to enable the modeling of such relationships. We collect dense annotations of objects, attributes, and relationships within each image to learn these models. Specifically, our dataset contains over 108K images where each image has an average of $$35$$35 objects, $$26$$26 attributes, and $$21$$21 pairwise relationships between objects. We canonicalize the objects, attributes, relationships, and noun phrases in region descriptions and questions answer pairs to WordNet synsets. Together, these annotations represent the densest and largest dataset of image descriptions, objects, attributes, relationships, and question answer pairs.

/pdf/visual-genome-connecting-language-and-vision-using-15ih2ylk6r.pdf

Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

Despite progress in perceptual tasks such as image classification, computers still perform poorly on cognitive tasks such as image description and question answering. Cognition is core to tasks that involve not just recognizing, but reasoning about our visual world. However, models used to tackle the rich content in images for cognitive tasks are still being trained using the same datasets designed for perceptual tasks. To achieve success at cognitive tasks, models need to understand the interactions and relationships between objects in an image. When asked "What vehicle is the person riding?", computers will need to identify the objects in an image as well as the relationships riding(man, carriage) and pulling(horse, carriage) in order to answer correctly that "the person is riding a horse-drawn carriage". 
In this paper, we present the Visual Genome dataset to enable the modeling of such relationships. We collect dense annotations of objects, attributes, and relationships within each image to learn these models. Specifically, our dataset contains over 100K images where each image has an average of 21 objects, 18 attributes, and 18 pairwise relationships between objects. We canonicalize the objects, attributes, relationships, and noun phrases in region descriptions and questions answer pairs to WordNet synsets. Together, these annotations represent the densest and largest dataset of image descriptions, objects, attributes, relationships, and question answers.

We have seen great progress in basic perceptual tasks such as object recognition and detection. However, AI models still fail to match humans in high-level vision tasks due to the lack of capacities for deeper reasoning. Recently the new task of visual question answering (QA) has been proposed to evaluate a model's capacity for deep image understanding. Previous works have established a loose, global association between QA sentences and images. However, many questions and answers, in practice, relate to local regions in the images. We establish a semantic link between textual descriptions and image regions by object-level grounding. It enables a new type of QA with visual answers, in addition to textual answers used in previous work. We study the visual QA tasks in a grounded setting with a large collection of 7W multiple-choice QA pairs. Furthermore, we evaluate human performance and several baseline models on the QA tasks. Finally, we propose a novel LSTM model with spatial attention to tackle the 7W QA tasks.

/pdf/visual7w-grounded-question-answering-in-images-1isor8tzku.pdf

Visual7W: Grounded Question Answering in Images

Physical intuition is pivotal for intelligent agents to perform complex tasks. In this paper we investigate the passive acquisition of an intuitive understanding of physical principles as well as the active utilisation of this intuition in the context of generalised object stacking. To this end, we provide ShapeStacks (Source code & data are available at http://shapestacks.robots.ox.ac.uk): a simulation-based dataset featuring 20,000 stack configurations composed of a variety of elementary geometric primitives richly annotated regarding semantics and structural stability. We train visual classifiers for binary stability prediction on the ShapeStacks data and scrutinise their learned physical intuition. Due to the richness of the training data our approach also generalises favourably to real-world scenarios achieving state-of-the-art stability prediction on a publicly available benchmark of block towers. We then leverage the physical intuition learned by our model to actively construct stable stacks and observe the emergence of an intuitive notion of stackability - an inherent object affordance - induced by the active stacking task. Our approach performs well exceeding the stack height observed during training and even manages to counterbalance initially unstable structures.

https://openaccess.thecvf.com/content_ECCV_2018/papers/Oliver_Groth_ShapeStacks_Learning_Vision-Based_ECCV_2018_paper.pdf

ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking

This paper addresses the task of designing a modular neural network architecture that jointly solves different tasks. As an example we use the tasks of depth estimation and semantic segmentation given a single RGB image. The main focus of this work is to analyze the cross-modality influence between depth and semantic prediction maps on their joint refinement. While most of the previous works solely focus on measuring improvements in accuracy, we propose a way to quantify the cross-modality influence. We show that there is a relationship between final accuracy and cross-modality influence, although not a simple linear one. Hence a larger cross-modality influence does not necessarily translate into an improved accuracy. We find that a beneficial balance between the cross-modality influences can be achieved by network architecture and conjecture that this relationship can be utilized to understand different network design choices. Towards this end we propose a Convolutional Neural Network (CNN) architecture that fuses the state-of-the-art results for depth estimation and semantic labeling. By balancing the cross-modality influences between depth and semantic prediction, we achieve improved results for both tasks using the NYU-Depth v2 benchmark.

Oliver Groth

Papers

Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

Visual7W: Grounded Question Answering in Images

ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking

Analyzing modular CNN architectures for joint depth prediction and semantic segmentation