Related papers: Adversarial Inference for Multi-Sentence Video Des…

The majority of adversarial machine learning research focuses on additive attacks, which add adversarial perturbation to input data. On the other hand, unlike image recognition problems, only a handful of attack approaches have been…

Existing long video retrieval systems are trained and tested in the paragraph-to-video retrieval regime, where every long video is described by a single long paragraph. This neglects the richness and variety of possible valid descriptions…

Generating relevant responses in a dialog is challenging, and requires not only proper modeling of context in the conversation but also being able to generate fluent sentences during inference. In this paper, we propose a two-step framework…

The Image Difference Captioning (IDC) task aims to describe the visual differences between two similar images with natural language. The major challenges of this task lie in two aspects: 1) fine-grained visual differences that require…

The existing image captioning approaches typically train a one-stage sentence decoder, which is difficult to generate rich fine-grained descriptions. On the other hand, multi-stage image caption model is hard to train due to the vanishing…

Adversarial examples are helpful for analyzing and improving the robustness of text classifiers. Generating high-quality adversarial examples is a challenging task as it requires generating fluent adversarial sentences that are semantically…

Video captioning is an advanced multi-modal task which aims to describe a video clip using a natural language sentence. The encoder-decoder framework is the most popular paradigm for this task in recent years. However, there exist some…

Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both methods require making…

Video captioning aims to describe video contents using natural language format that involves understanding and interpreting scenes, actions and events that occurs simultaneously on the view. Current approaches have mainly concentrated on…

As audio/visual classification models are widely deployed for sensitive tasks like content filtering at scale, it is critical to understand their robustness along with improving the accuracy. This work aims to study several key questions…

It is shown that many published models for the Stanford Question Answering Dataset (Rajpurkar et al., 2016) lack robustness, suffering an over 50% decrease in F1 score during adversarial evaluation based on the AddSent (Jia and Liang, 2017)…

Many machine learning classifiers are vulnerable to adversarial perturbations. An adversarial perturbation modifies an input to change a classifier's prediction without causing the input to seem substantially different to human perception.…

Automatic video description requires the generation of natural language statements about the actions, events, and objects in the video. An important human trait, when we describe a video, is that we are able to do this with variable levels…

The goal of video summarization is to automatically shorten videos such that it conveys the overall story without losing relevant information. In many application scenarios, improper video summarization can have a large impact. For example…

Video captioning has shown impressive progress in recent years. One key reason of the performance improvements made by existing methods lie in massive paired video-sentence data, but collecting such strong annotation, i.e., high-quality…

In this paper we propose a novel method for detecting adversarial examples by training a binary classifier with both origin data and saliency data. In the case of image classification model, saliency simply explain how the model make…

Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial…

The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may lead the generator to…

Most of the existing works in video synthesis focus on generating videos using adversarial learning. Despite their success, these methods often require input reference frame or fail to generate diverse videos from the given data…

Adversarial learning methods have been proposed for a wide range of applications, but the training of adversarial models can be notoriously unstable. Effectively balancing the performance of the generator and discriminator is critical,…