Related papers: The Devil is in the Spurious Correlations: Boostin…
To address the problem of NLP classifiers learning spurious correlations between training features and target labels, a common approach is to make the model's predictions invariant to these features. However, this can be counter-productive…
Video moment localization aims to retrieve the target segment of an untrimmed video according to the natural language query. Weakly supervised methods gains attention recently, as the precise temporal location of the target segment is not…
Recently, NLP models have achieved remarkable progress across a variety of tasks; however, they have also been criticized for being not robust. Many robustness problems can be attributed to models exploiting spurious correlations, or…
Identifying spurious correlations learned by a trained model is at the core of refining a trained model and building a trustworthy model. We present a simple method to identify spurious correlations that have been learned by a model trained…
Content-based video retrieval is one of the most challenging tasks in surveillance systems. In this study, Latent Dirichlet Allocation (LDA) topic model is used to annotate surveillance videos in an unsupervised manner. In scene…
Recent years have witnessed the great success of self-supervised learning (SSL) in recommendation systems. However, SSL recommender models are likely to suffer from spurious correlations, leading to poor generalization. To mitigate spurious…
Precise video retrieval requires multi-modal correlations to handle unseen vocabulary and scenes, becoming more complex for lengthy videos where models must perform effectively without prior training on a specific dataset. We introduce a…
Deep neural classifiers tend to rely on spurious correlations between spurious attributes of inputs and targets to make predictions, which could jeopardize their generalization capability. Training classifiers robust to spurious…
Recent advancements in Large Language Models (LLMs) have significantly enhanced their capacity to process long contexts. However, effectively utilizing this long context remains a challenge due to the issue of distraction, where irrelevant…
Scene text retrieval aims to localize and search all text instances from an image gallery, which are the same or similar to a given query text. Such a task is usually realized by matching a query text to the recognized words, outputted by…
Existing scene text recognition (STR) methods struggle to recognize challenging texts, especially for artistic and severely distorted characters. The limitation lies in the insufficient exploration of character morphologies, including the…
Video moment retrieval and highlight detection have received attention in the current era of video content proliferation, aiming to localize moments and estimate clip relevances based on user-specific queries. Given that the video content…
Video moment retrieval aims to localize the target moment in an video according to the given sentence. The weak-supervised setting only provides the video-level sentence annotations during training. Most existing weak-supervised methods…
Context information in search sessions has proven to be useful for capturing user search intent. Existing studies explored user behavior sequences in sessions in different ways to enhance query suggestion or document ranking. However, a…
Many studies focus on improving pretraining or developing new backbones in text-video retrieval. However, existing methods may suffer from the learning and inference bias issue, as recent research suggests in other text-video-related tasks.…
Modern sequential recommender systems commonly use transformer-based models for next-item prediction. While these models demonstrate a strong balance between efficiency and quality, integrating interleaving features - such as the query…
In-context learning (ICL) enables generalization to new tasks with minimal labeled data. However, mainstream ICL approaches rely on a gridding strategy, which lacks the flexibility required for vision applications. We introduce Temporal, a…
Understanding temporal dynamics of video is an essential aspect of learning better video representations. Recently, transformer-based architectural designs have been extensively explored for video tasks due to their capability to capture…
Machine learning models are known to learn spurious correlations, i.e., features having strong relations with class labels but no causal relation. Relying on those correlations leads to poor performance in the data groups without these…
Video anomaly detection aims to discover abnormal events in videos, and the principal objects are target objects such as people and vehicles. Each target in the video data has rich spatio-temporal context information. Most existing methods…