Christopher Thomas

Christopher Thomas, Yipeng Zhang, Shih-Fu Chang

Visual entailment is a recently proposed multimodal reasoning task where the goal is to predict the logical relationship of a piece of text to an image. In this paper, we propose an extension of this task, where the goal is to predict the logical relationship of fine-grained knowledge elements within a piece of text to an image. Unlike prior work, our method is inherently explainable and makes logical predictions at different levels of granularity. Because we lack fine-grained labels to train our method, we propose a novel multi-instance learning approach which learns a fine-grained labeling using only sample-level supervision. We also impose novel semantic structural constraints which ensure that fine-grained predictions are internally semantically consistent. We evaluate our method on a new dataset of manually annotated knowledge elements and show that our method achieves 68.18\% accuracy at this challenging task while significantly outperforming several strong baselines. Finally, we present extensive qualitative results illustrating our method's predictions and the visual evidence our method relied on. Our code and annotated dataset can be found here: https://github.com/SkrighYZ/FGVE.

Long Chen, Yulei Niu, Brian Chen et al.

Given a long untrimmed video and natural language queries, video grounding (VG) aims to temporally localize the semantically-aligned video segments. Almost all existing VG work holds two simple but unrealistic assumptions: 1) All query sentences can be grounded in the corresponding video. 2) All query sentences for the same video are always at the same semantic scale. Unfortunately, both assumptions make today's VG models fail to work in practice. For example, in real-world multimodal assets (eg, news articles), most of the sentences in the article can not be grounded in their affiliated videos, and they typically have rich hierarchical relations (ie, at different semantic scales). To this end, we propose a new challenging grounding task: Weakly-Supervised temporal Article Grounding (WSAG). Specifically, given an article and a relevant video, WSAG aims to localize all ``groundable'' sentences to the video, and these sentences are possibly at different semantic scales. Accordingly, we collect the first WSAG dataset to facilitate this task: YouwikiHow, which borrows the inherent multi-scale descriptions in wikiHow articles and plentiful YouTube videos. In addition, we propose a simple but effective method DualMIL for WSAG, which consists of a two-level MIL loss and a single-/cross- sentence constraint loss. These training objectives are carefully designed for these relaxed assumptions. Extensive ablations have verified the effectiveness of DualMIL.

Hammad A. Ayyubi, Christopher Thomas, Lovish Chum et al.

Events describe happenings in our world that are of importance. Naturally, understanding events mentioned in multimedia content and how they are related forms an important way of comprehending our world. Existing literature can infer if events across textual and visual (video) domains are identical (via grounding) and thus, on the same semantic level. However, grounding fails to capture the intricate cross-event relations that exist due to the same events being referred to on many semantic levels. For example, in Figure 1, the abstract event of "war" manifests at a lower semantic level through subevents "tanks firing" (in video) and airplane "shot" (in text), leading to a hierarchical, multimodal relationship between the events. In this paper, we propose the task of extracting event hierarchies from multimodal (video and text) data to capture how the same event manifests itself in different modalities at different semantic levels. This reveals the structure of events and is critical to understanding them. To support research on this task, we introduce the Multimodal Hierarchical Events (MultiHiEve) dataset. Unlike prior video-language datasets, MultiHiEve is composed of news video-article pairs, which makes it rich in event hierarchies. We densely annotate a part of the dataset to construct the test benchmark. We show the limitations of state-of-the-art unimodal and multimodal baselines on this task. Further, we address these limitations via a new weakly supervised model, leveraging only unannotated video-article pairs from MultiHiEve. We perform a thorough evaluation of our proposed method which demonstrates improved performance on this task and highlight opportunities for future research.

Alvi Md Ishmam, Christopher Thomas

In recent years there has been enormous interest in vision-language models trained using self-supervised objectives. However, the use of large-scale datasets scraped from the web for training also makes these models vulnerable to potential security threats, such as backdooring and poisoning attacks. In this paper, we propose a method for mitigating such attacks on contrastively trained vision-language models. Our approach leverages external knowledge extracted from a language model to prevent models from learning correlations between image regions which lack strong alignment with external knowledge. We do this by imposing constraints to enforce that attention paid by the model to visual regions is proportional to the alignment of those regions with external knowledge. We conduct extensive experiments using a variety of recent backdooring and poisoning attacks on multiple datasets and architectures. Our results clearly demonstrate that our proposed approach is highly effective at defending against such attacks across multiple settings, while maintaining model utility and without requiring any changes at inference time

Mingyang Zhou, Yi R. Fung, Long Chen et al.

Building cross-model intelligence that can understand charts and communicate the salient information hidden behind them is an appealing challenge in the vision and language(V+L) community. The capability to uncover the underlined table data of chart figures is a critical key to automatic chart understanding. We introduce ChartT5, a V+L model that learns how to interpret table information from chart images via cross-modal pre-training on plot table pairs. Specifically, we propose two novel pre-training objectives: Masked Header Prediction (MHP) and Masked Value Prediction (MVP) to facilitate the model with different skills to interpret the table information. We have conducted extensive experiments on chart question answering and chart summarization to verify the effectiveness of the proposed pre-training strategies. In particular, on the ChartQA benchmark, our ChartT5 outperforms the state-of-the-art non-pretraining methods by over 8% performance gains.

Brian Chen, Xudong Lin, Christopher Thomas et al.

Visual and textual modalities contribute complementary information about events described in multimedia documents. Videos contain rich dynamics and detailed unfoldings of events, while text describes more high-level and abstract concepts. However, existing event extraction methods either do not handle video or solely target video while ignoring other modalities. In contrast, we propose the first approach to jointly extract events from video and text articles. We introduce the new task of Video MultiMedia Event Extraction (Video M2E2) and propose two novel components to build the first system towards this task. First, we propose the first self-supervised multimodal event coreference model that can determine coreference between video events and text events without any manually annotated pairs. Second, we introduce the first multimodal transformer which extracts structured event information jointly from both videos and text documents. We also construct and will publicly release a new benchmark of video-article pairs, consisting of 860 video-article pairs with extensive annotations for evaluating methods on this task. Our experimental results demonstrate the effectiveness of our proposed method on our new benchmark dataset. We achieve 6.0% and 5.8% absolute F-score gain on multimodal event coreference resolution and multimedia event extraction.

Christopher Thomas, Yale Song, Adriana Kovashka

We study the problem of animating images by transferring spatio-temporal visual effects (such as melting) from a collection of videos. We tackle two primary challenges in visual effect transfer: 1) how to capture the effect we wish to distill; and 2) how to ensure that only the effect, rather than content or artistic style, is transferred from the source videos to the input image. To address the first challenge, we evaluate five loss functions; the most promising one encourages the generated animations to have similar optical flow and texture motions as the source videos. To address the second challenge, we only allow our model to move existing image pixels from the previous frame, rather than predicting unconstrained pixel values. This forces any visual effects to occur using the input image's pixels, preventing unwanted artistic style or content from the source video from appearing in the output. We evaluate our method in objective and subjective settings, and show interesting qualitative results which demonstrate objects undergoing atypical transformations, such as making a face melt or a deer bloom.

Christopher Thomas, Adriana Kovashka

The abundance of multimodal data (e.g. social media posts) has inspired interest in cross-modal retrieval methods. Popular approaches rely on a variety of metric learning losses, which prescribe what the proximity of image and text should be, in the learned space. However, most prior methods have focused on the case where image and text convey redundant information; in contrast, real-world image-text pairs convey complementary information with little overlap. Further, images in news articles and media portray topics in a visually diverse fashion; thus, we need to take special care to ensure a meaningful image representation. We propose novel within-modality losses which encourage semantic coherency in both the text and image subspaces, which does not necessarily align with visual coherency. Our method ensures that not only are paired images and texts close, but the expected image-image and text-text relationships are also observed. Our approach improves the results of cross-modal retrieval on four datasets compared to five baselines.

Christopher Thomas, Adriana Kovashka

The news media shape public opinion, and often, the visual bias they contain is evident for human observers. This bias can be inferred from how different media sources portray different subjects or topics. In this paper, we model visual political bias in contemporary media sources at scale, using webly supervised data. We collect a dataset of over one million unique images and associated news articles from left- and right-leaning news sources, and develop a method to predict the image's political leaning. This problem is particularly challenging because of the enormous intra-class visual and semantic diversity of our data. We propose a two-stage method to tackle this problem. In the first stage, the model is forced to learn relevant visual concepts that, when joined with document embeddings computed from articles paired with the images, enable the model to predict bias. In the second stage, we remove the requirement of the text domain and train a visual classifier from the features of the former model. We show this two-stage approach facilitates learning and outperforms several strong baselines. We also present extensive qualitative results demonstrating the nuances of the data.

Christopher Thomas, Adriana Kovashka

Computer vision systems currently lack the ability to reliably recognize artistically rendered objects, especially when such data is limited. In this paper, we propose a method for recognizing objects in artistic modalities (such as paintings, cartoons, or sketches), without requiring any labeled data from those modalities. Our method explicitly accounts for stylistic domain shifts between and within domains. To do so, we introduce a complementary training modality constructed to be similar in artistic style to the target domain, and enforce that the network learns features that are invariant between the two training modalities. We show how such artificial labeled source domains can be generated automatically through the use of style transfer techniques, using diverse target images to represent the style in the target domain. Unlike existing methods which require a large amount of unlabeled target data, our method can work with as few as ten unlabeled images. We evaluate it on a number of cross-domain object and scene classification tasks and on a new dataset we release. Our experiments show that our approach, though conceptually simple, significantly improves the accuracy that existing domain adaptation techniques obtain for artistic object recognition.

Christopher Thomas, Adriana Kovashka

In this paper, we examine the visual variability of objects across different ad categories, i.e. what causes an advertisement to be visually persuasive. We focus on modeling and generating faces which appear to come from different types of ads. For example, if faces in beauty ads tend to be women wearing lipstick, a generative model should portray this distinct visual appearance. Training generative models which capture such category-specific differences is challenging because of the highly diverse appearance of faces in ads and the relatively limited amount of available training data. To address these problems, we propose a conditional variational autoencoder which makes use of predicted semantic attributes and facial expressions as a supervisory signal when training. We show how our model can be used to produce visually distinct faces which appear to be from a fixed ad topic category. Our human studies and quantitative and qualitative experiments confirm that our method greatly outperforms a variety of baselines, including two variations of a state-of-the-art generative adversarial network, for transforming faces to be more ad-category appropriate. Finally, we show preliminary generation results for other types of objects, conditioned on an ad topic.

Zaeem Hussain, Mingda Zhang, Xiaozhong Zhang et al.

There is more to images than their objective physical content: for example, advertisements are created to persuade a viewer to take a certain action. We propose the novel problem of automatic advertisement understanding. To enable research on this problem, we create two datasets: an image dataset of 64,832 image ads, and a video dataset of 3,477 ads. Our data contains rich annotations encompassing the topic and sentiment of the ads, questions and answers describing what actions the viewer is prompted to take and the reasoning that the ad presents to persuade the viewer ("What should I do according to this ad, and why should I do it?"), and symbolic references ads make (e.g. a dove symbolizes peace). We also analyze the most common persuasive strategies ads use, and the capabilities that computer vision systems should have to understand these strategies. We present baseline classification results for several prediction tasks, including automatically answering questions about the messages of the ads.

Christopher Thomas

In this technical report, we present our publicly downloadable implementation of the SALICON saliency model. At the time of this writing, SALICON is one of the top performing saliency models on the MIT 300 fixation prediction dataset which evaluates how well an algorithm is able to predict where humans would look in a given image. Recently, numerous models have achieved state-of-the-art performance on this benchmark, but none of the top 5 performing models (including SALICON) are available for download. To address this issue, we have created a publicly downloadable implementation of the SALICON model. It is our hope that our model will engender further research in visual attention modeling by providing a baseline for comparison of other algorithms and a platform for extending this implementation. The model we provide supports both training and testing, enabling researchers to quickly fine-tune the model on their own dataset. We also provide a pre-trained model and code for those users who only need to generate saliency maps for images without training their own model.

Christopher Thomas, Adriana Kovashka

We introduce the novel problem of identifying the photographer behind a photograph. To explore the feasibility of current computer vision techniques to address this problem, we created a new dataset of over 180,000 images taken by 41 well-known photographers. Using this dataset, we examined the effectiveness of a variety of features (low and high-level, including CNN features) at identifying the photographer. We also trained a new deep convolutional neural network for this task. Our results show that high-level features greatly outperform low-level features. We provide qualitative results using these learned models that give insight into our method's ability to distinguish between photographers, and allow us to draw interesting conclusions about what specific photographers shoot. We also demonstrate two applications of our method.

Christopher Thomas, Brandon Jennings

Mobile devices with touch keyboards have become ubiquitous, but text entry on these devices remains slow and errorprone. Understanding touch patterns during text entry could be useful in designing robust error-correction algorithms for soft keyboards. In this paper, we present an analysis of text input behaviors on a soft QWERTY keyboard in three different text entry postures: index finger only, one thumb, and two thumb. Our work expands on the work of [1] by considering the entire surface area of digit contact with the smartphone keyboard, rather than interpreting each touch as a single point. To do this, we captured touch areas for every key in a lab study with 8 participants and calculated offsets, error rates, and size measurements. We then repeated the original experiment described in [1] and showed that significant differences exist when basing offset calculations on touch area compared to touch points for two postures.