arXiv subjects

Tanmay Gupta

Publications and source records attributed to Tanmay Gupta.

26 records · Page 2Linked to original sources

arXiv2021

Visual Semantic Role Labeling for Video Understanding

We propose a new framework for understanding and representing related salient events in a video using visual semantic role labeling. We represent videos as a set of related events, wherein each event consists of a verb and multiple entities that fulfill various roles relevant to that event. To study the challenging task of semantic role labeling in videos or VidSRL, we introduce 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. Entities are co-referenced across events within a movie clip and events are connected to each other via event-event relations. Clips in VidSitu are drawn from a large collection of movies (${\sim}3K$) and have been chosen to be both complex (${\sim}4.2$ unique verbs within a video) as well as diverse (${\sim}200$ verbs have more than $100$ annotations each). We provide 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. Our code and dataset is available at vidsitu.org.

cs.CV↗

arXiv2020

Contrastive Learning for Weakly Supervised Phrase Grounding

Phrase grounding, the problem of associating image regions to caption words, is a crucial component of vision-language tasks. We show that phrase grounding can be learned by optimizing word-region attention to maximize a lower bound on mutual information between images and caption words. Given pairs of images and captions, we maximize compatibility of the attention-weighted regions and the words in the corresponding caption, compared to non-corresponding pairs of images and captions. A key idea is to construct effective negative captions for learning through language model guided word substitutions. Training with our negatives yields a $\sim10\%$ absolute gain in accuracy over randomly-sampled negatives from the training data. Our weakly supervised phrase grounding model trained on COCO-Captions shows a healthy gain of $5.7\%$ to achieve $76.7\%$ accuracy on Flickr30K Entities benchmark.

cs.CV↗

arXiv2020

The Classification of Magic SET Squares

A magic SET square is a 3 by 3 table of SET cards such that each row, column, diagonal, and anti-diagonal is a set. We allow the following transformations of the square: shuffling features, shuffling values within the features, rotations and reflections of the square. Under these transformations, there are 21 types of magic SET squares. We calculate the number of squares of each type. In addition, we discuss a game of SET tic-tac-toe.

math.HO↗

arXiv2019

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 sophisticated approaches. Our model includes factors for detection scores, human and object appearance, and coarse (box-pair configuration) and optionally fine-grained layout (human pose). We also develop training techniques that improve learning efficiency by: (1) eliminating a train-inference mismatch; (2) rejecting easy negatives during mini-batch training; and (3) using a ratio of negatives to positives that is two orders of magnitude larger than existing approaches. We conduct a thorough ablation study to understand the importance of different factors and training techniques using the challenging HICO-Det dataset.

cs.CV↗

arXiv2019

ViCo: Word Embeddings from Visual Co-occurrences

We propose to learn word embeddings from visual co-occurrences. Two words co-occur visually if both words apply to the same image or image region. Specifically, we extract four types of visual co-occurrences between object and attribute words from large-scale, textually-annotated visual databases like VisualGenome and ImageNet. We then train a multi-task log-bilinear model that compactly encodes word "meanings" represented by each co-occurrence type into a single visual word-vector. Through unsupervised clustering, supervised partitioning, and a zero-shot-like generalization analysis we show that our word embeddings complement text-only embeddings like GloVe by better representing similarities and differences between visual concepts that are difficult to obtain from text corpora alone. We further evaluate our embeddings on five downstream applications, four of which are vision-language tasks. Augmenting GloVe with our embeddings yields gains on all tasks. We also find that random embeddings perform comparably to learned embeddings on all supervised vision-language tasks, contrary to conventional wisdom.

cs.CV↗

arXiv2018

Imagine This! Scripts to Compositions to Videos

Imagining a scene described in natural language with realistic layout and appearance of entities is the ultimate test of spatial, visual, and semantic world knowledge. Towards this goal, we present the Composition, Retrieval, and Fusion Network (CRAFT), a model capable of learning this knowledge from video-caption data and applying it while generating videos from novel captions. CRAFT explicitly predicts a temporal-layout of mentioned entities (characters and objects), retrieves spatio-temporal entity segments from a video database and fuses them to generate scene videos. Our contributions include sequential training of components of CRAFT while jointly modeling layout and appearances, and losses that encourage learning compositional representations for retrieval. We evaluate CRAFT on semantic fidelity to caption, composition consistency, and visual quality. CRAFT outperforms direct pixel generation approaches and generalizes well to unseen captions and to unseen video databases with no text annotations. We demonstrate CRAFT on FLINTSTONES, a new richly annotated video-caption dataset with over 25000 videos. For a glimpse of videos generated by CRAFT, see https://youtu.be/688Vv86n0z8.

cs.CV↗

arXiv2017

Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks

An important goal of computer vision is to build systems that learn visual representations over time that can be applied to many tasks. In this paper, we investigate a vision-language embedding as a core representation and show that it leads to better cross-task transfer than standard multi-task learning. In particular, the task of visual recognition is aligned to the task of visual question answering by forcing each to use the same word-region embeddings. We show this leads to greater inductive transfer from recognition to VQA than standard multitask learning. Visual recognition also improves, especially for categories that have relatively few recognition training labels but appear often in the VQA setting. Thus, our paper takes a small step towards creating more general vision systems by showing the benefit of interpretable, flexible, and trainable core representations.

cs.CV↗

arXiv2016

3DFS: Deformable Dense Depth Fusion and Segmentation for Object Reconstruction from a Handheld Camera

We propose an approach for 3D reconstruction and segmentation of a single object placed on a flat surface from an input video. Our approach is to perform dense depth map estimation for multiple views using a proposed objective function that preserves detail. The resulting depth maps are then fused using a proposed implicit surface function that is robust to estimation error, producing a smooth surface reconstruction of the entire scene. Finally, the object is segmented from the remaining scene using a proposed 2D-3D segmentation that incorporates image and depth cues with priors and regularization over the 3D volume and 2D segmentations. We evaluate 3D reconstructions qualitatively on our Object-Videos dataset, comparing to fusion, multiview stereo, and segmentation baselines. We also quantitatively evaluate the dense depth estimation using the RGBD Scenes V2 dataset [Henry et al. 2013] and the segmentation using keyframe annotations of the Object-Videos dataset.

cs.CV↗