Ranjitha Kumar

Samarth Mishra, Zhongping Zhang, Yuan Shen et al.

Measuring similarity between two images often requires performing complex reasoning along different axes (e.g., color, texture, or shape). Insights into what might be important for measuring similarity can can be provided by annotated attributes, but prior work tends to view these annotations as complete, resulting in them using a simplistic approach of predicting attributes on single images, which are, in turn, used to measure similarity. However, it is impractical for a dataset to fully annotate every attribute that may be important. Thus, only representing images based on these incomplete annotations may miss out on key information. To address this issue, we propose the Pairwise Attribute-informed similarity Network (PAN), which breaks similarity learning into capturing similarity conditions and relevance scores from a joint representation of two images. This enables our model to identify that two images contain the same attribute, but can have it deemed irrelevant (e.g., due to fine-grained differences between them) and ignored for measuring similarity between the two images. Notably, while prior methods of using attribute annotations are often unable to outperform prior art, PAN obtains a 4-9% improvement on compatibility prediction between clothing items on Polyvore Outfits, a 5% gain on few shot classification of images using Caltech-UCSD Birds (CUB), and over 1% boost to Recall@1 on In-Shop Clothes Retrieval. Implementation available at https://github.com/samarth4149/PAN

Andrea Burns, Deniz Arsan, Sanjna Agrawal et al.

Vision-language navigation (VLN), in which an agent follows language instruction in a visual environment, has been studied under the premise that the input command is fully feasible in the environment. Yet in practice, a request may not be possible due to language ambiguity or environment changes. To study VLN with unknown command feasibility, we introduce a new dataset Mobile app Tasks with Iterative Feedback (MoTIF), where the goal is to complete a natural language command in a mobile app. Mobile apps provide a scalable domain to study real downstream uses of VLN methods. Moreover, mobile app commands provide instruction for interactive navigation, as they result in action sequences with state changes via clicking, typing, or swiping. MoTIF is the first to include feasibility annotations, containing both binary feasibility labels and fine-grained labels for why tasks are unsatisfiable. We further collect follow-up questions for ambiguous queries to enable research on task uncertainty resolution. Equipped with our dataset, we propose the new problem of feasibility prediction, in which a natural language instruction and multimodal app environment are used to predict command feasibility. MoTIF provides a more realistic app dataset as it contains many diverse environments, high-level goals, and longer action sequences than prior work. We evaluate interactive VLN methods using MoTIF, quantify the generalization ability of current approaches to new app environments, and measure the effect of task feasibility on navigation performance.

Andrea Burns, Deniz Arsan, Sanjna Agrawal et al.

In recent years, vision-language research has shifted to study tasks which require more complex reasoning, such as interactive question answering, visual common sense reasoning, and question-answer plausibility prediction. However, the datasets used for these problems fail to capture the complexity of real inputs and multimodal environments, such as ambiguous natural language requests and diverse digital domains. We introduce Mobile app Tasks with Iterative Feedback (MoTIF), a dataset with natural language commands for the greatest number of interactive environments to date. MoTIF is the first to contain natural language requests for interactive environments that are not satisfiable, and we obtain follow-up questions on this subset to enable research on task uncertainty resolution. We perform initial feasibility classification experiments and only reach an F1 score of 37.3, verifying the need for richer vision-language representations and improved architectures to reason about task feasibility.

Yuan Shen, Shanduojiao Jiang, Muhammad Rizky Wellyanto et al.

When people talk about fashion, they care about the underlying meaning of fashion concepts,e.g., style.For example, people ask questions like what features make this dress smart.However, the product descriptions in today fashion websites are full of domain specific and low level words. It is not clear to people how exactly those low level descriptions can contribute to a style or any high level fashion concept. In this paper, we proposed a data driven solution to address this concept understanding issues by leveraging a large number of existing product data on fashion sites. We first collected and categorized 1546 fashion keywords into 5 different fashion categories. Then, we collected a new fashion product dataset with 853,056 products in total. Finally, we trained a deep learning model that can explicitly predict and explain high level fashion concepts in a product image with its low level and domain specific fashion features.

Mariya I. Vasileva, Bryan A. Plummer, Krishna Dusad et al.

Outfits in online fashion data are composed of items of many different types (e.g. top, bottom, shoes) that share some stylistic relationship with one another. A representation for building outfits requires a method that can learn both notions of similarity (for example, when two tops are interchangeable) and compatibility (items of possibly different type that can go together in an outfit). This paper presents an approach to learning an image embedding that respects item type, and jointly learns notions of item similarity and compatibility in an end-to-end model. To evaluate the learned representation, we crawled 68,306 outfits created by users on the Polyvore website. Our approach obtains 3-5% improvement over the state-of-the-art on outfit compatibility prediction and fill-in-the-blank tasks using our dataset, as well as an established smaller dataset, while supporting a variety of useful queries.

Haizi Yu, Lav R. Varshney, Guy E. Garnett et al.

Throughout music history, theorists have identified and documented interpretable rules that capture the decisions of composers. This paper asks, "Can a machine behave like a music theorist?" It presents MUS-ROVER, a self-learning system for automatically discovering rules from symbolic music. MUS-ROVER performs feature learning via $n$-gram models to extract compositional rules --- statistical patterns over the resulting features. We evaluate MUS-ROVER on Bach's (SATB) chorales, demonstrating that it can recover known rules, as well as identify new, characteristic patterns for further study. We discuss how the extracted rules can be used in both machine and human composition.