相关论文: FineCausal: A Causal-Based Framework for Interpret…

Despite the impressive performance of vision-language models (VLMs) on downstream tasks, their ability to understand and reason about causal relationships in visual inputs remains unclear. Robust causal reasoning is fundamental to solving…

Unsupervised semantic segmentation aims to achieve high-quality semantic grouping without human-labeled annotations. With the advent of self-supervised pre-training, various frameworks utilize the pre-trained features to train prediction…

Long-term Action Quality Assessment (AQA) aims to evaluate the quantitative performance of actions in long videos. However, existing methods face challenges due to domain shifts between the pre-trained large-scale action recognition…

The goal of the YouMakeup VQA Challenge 2020 is to provide a common benchmark for fine-grained action understanding in domain-specific videos e.g. makeup instructional videos. We propose two novel question-answering tasks to evaluate…

Action quality assessment (AQA) is an active research problem in video-based applications that is a challenging task due to the score variance per frame. Existing methods address this problem via convolutional-based approaches but suffer…

GraphRAG-Causal introduces an innovative framework that combines graph-based retrieval with large language models to enhance causal reasoning in news analysis. Traditional NLP approaches often struggle with identifying complex, implicit…

Attention mechanism has demonstrated great potential in fine-grained visual recognition tasks. In this paper, we present a counterfactual attention learning method to learn more effective attention based on causal inference. Unlike most…

Visual Question Answering (VQA) models have achieved significant success in recent times. Despite the success of VQA models, they are mostly black-box models providing no reasoning about the predicted answer, thus raising questions for…

Action quality assessment (AQA) aims at automatically judging human action based on a video of the said action and assigning a performance score to it. The majority of works in the existing literature on AQA divide RGB videos into short…

Building benchmarks to systemically analyze different capabilities of video question answering (VideoQA) models is challenging yet crucial. Existing benchmarks often use non-compositional simple questions and suffer from language biases,…

We use a deep Koopman operator-theoretic formalism to develop a novel causal discovery algorithm, Kausal. Causal discovery aims to identify cause-effect mechanisms for better scientific understanding, explainable decision-making, and more…

As systems are getting more autonomous with the development of artificial intelligence, it is important to discover the causal knowledge from observational sensory inputs. By encoding a series of cause-effect relations between events,…

Portfolio managers rely on correlation-based analysis and heuristic methods that fail to capture true causal relationships driving performance. We present a hybrid framework that integrates statistical causal discovery algorithms with…

Temporal action localization (TAL) is an important and challenging problem in video understanding. However, most existing TAL benchmarks are built upon the coarse granularity of action classes, which exhibits two major limitations in this…

Image quality assessment (IQA) is inherently complex, as it reflects both the quantification and interpretation of perceptual quality rooted in the human visual system. Conventional approaches typically rely on fixed models to output scalar…

Despite great success in modeling visual perception, deep neural network based image quality assessment (IQA) still remains unreliable in real-world applications due to its vulnerability to adversarial perturbations and the inexplicit…

Real-life applications of action recognition often require a fine-grained understanding of subtle movements, e.g., in sports analytics, user interactions in AR/VR, and surgical videos. Although fine-grained actions are more costly to…

Despite the outstanding performance of deep learning models in clinical prediction tasks, explainability remains a significant challenge. Inspired by transformer architectures, we introduce the Temporal-Feature Cross Attention Mechanism…

Causality has the potential to truly transform the way we solve a large number of real-world problems. Yet, so far, its potential largely remains to be unlocked as causality often requires crucial assumptions which cannot be tested in…

Many benchmarks for automated causal inference evaluate a system's performance based on a single numerical output, such as an Average Treatment Effect (ATE). This approach conflates two distinct steps in causal analysis: identification -…