Related papers: Ambiguous Images With Human Judgments for Robust V…
An interesting development in automatic visual recognition has been the emergence of tasks where it is not possible to assign objective labels to images, yet still feasible to collect annotations that reflect human judgements about them.…
Most publicly available image quality databases have been created under highly controlled conditions by introducing graded simulated distortions onto high-quality photographs. However, images captured using typical real-world mobile camera…
Recent visual pose estimation and tracking solutions provide notable results on popular datasets such as T-LESS and YCB. However, in the real world, we can find ambiguous objects that do not allow exact classification and detection from a…
Evaluation metrics for image captioning face two challenges. Firstly, commonly used metrics such as CIDEr, METEOR, ROUGE and BLEU often do not correlate well with human judgments. Secondly, each metric has well known blind spots to…
Automated fact-checking systems verify claims against evidence to predict their veracity. In real-world scenarios, the retrieved evidence may not unambiguously support or refute the claim and yield conflicting but valid interpretations.…
While existing video benchmarks largely consider specialized downstream tasks like retrieval or question-answering (QA), contemporary multimodal AI systems must be capable of well-rounded common-sense reasoning akin to human visual…
We consider the problem of sequential decision making on random fields corrupted by noise. In this scenario, the decision maker observes a noisy version of the data, yet judged with respect to the clean data. In particular, we first…
Ambiguity or uncertainty is a pervasive element of many real world decision making processes. Variation in decisions is a norm in this situation when the same problem is posed to different subjects. Psychological and metaphysical research…
Deep Learning has driven recent and exciting progress in computer vision, instilling the belief that these algorithms could solve any visual task. Yet, datasets commonly used to train and test computer vision algorithms have pervasive…
While the ImageNet dataset has been driving computer vision research over the past decade, significant label noise and ambiguity have made top-1 accuracy an insufficient measure of further progress. To address this, new label-sets and…
Deep networks thrive when trained on large scale data collections. This has given ImageNet a central role in the development of deep architectures for visual object classification. However, ImageNet was created during a specific period in…
Deep neural networks have achieved impressive performance on many computer vision benchmarks in recent years. However, can we be confident that impressive performance on benchmarks will translate to strong performance in real-world…
Equation learning aims to infer differential equation models from data. While a number of studies have shown that differential equation models can be successfully identified when the data are sufficiently detailed and corrupted with…
Photos serve as a way for humans to record what they experience in their daily lives, and they are often regarded as trustworthy sources of information. However, there is a growing concern that the advancement of artificial intelligence…
Visual Question Answering (VQA) is a core task for evaluating the capabilities of Vision-Language Models (VLMs). Existing VQA benchmarks primarily feature clear and unambiguous image-question pairs, whereas real-world scenarios often…
The one-shot Person Re-ID scenario faces two kinds of uncertainties when constructing the prediction model from $X$ to $Y$. The first is model uncertainty, which captures the noise of the parameters in DNNs due to a lack of training data.…
Much recent work on visual recognition aims to scale up learning to massive, noisily-annotated datasets. We address the problem of scaling- up the evaluation of such models to large-scale datasets with noisy labels. Current protocols for…
Image classification models often learn to predict a class based on irrelevant co-occurrences between input features and an output class in training data. We call the unwanted correlations "data biases," and the visual features causing data…
Deep neural networks are known to be data-driven and label noise can have a marked impact on model performance. Recent studies have shown great robustness to classic image recognition even under a high noisy rate. In medical applications,…
Multimedia event detection is the task of detecting a specific event of interest in an user-generated video on websites. The most fundamental challenge facing this task lies in the enormously varying quality of the video as well as the…