Related papers: Temporal Unlearnable Examples: Preventing Personal…

Text-based person search faces inherent limitations due to data scarcity, driven by stringent privacy constraints and the high cost of manual annotation. To mitigate this, existing methods usually rely on a Pretrain-then-Finetune paradigm,…

Multi-modal object tracking integrates auxiliary modalities such as depth, thermal infrared, event flow, and language to provide additional information beyond RGB images, showing great potential in improving tracking stabilization in…

Understanding temporal information and how the visual world changes over time is a fundamental ability of intelligent systems. In video understanding, temporal information is at the core of many current challenges, including compression,…

Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. While standard TAD follows fully supervised learning with closed-set setting on large training data, recent zero-shot…

Maintaining a catalog of Resident Space Objects (RSOs) can be cast in a typical Bayesian multi-object estimation problem, where the various sources of uncertainty in the problem - the orbital mechanics, the kinematic states of the…

Visual content memorability has intrigued the scientific community for decades, with applications ranging widely, from understanding nuanced aspects of human memory to enhancing content design. A significant challenge in progressing the…

In this paper, we propose the methods to handle temporal errors during multi-object tracking. Temporal error occurs when objects are occluded or noisy detections appear near the object. In those situations, tracking may fail and various…

Estimating treatment effects, especially individualized treatment effects (ITE), using observational data is challenging due to the complex situations of confounding bias. Existing approaches for estimating treatment effects from…

In widely used neural network-based collaborative filtering models, users' history logs are encoded into latent embeddings that represent the users' preferences. In this setting, the models are capable of mapping users' protected attributes…

Motion deblurring is a highly ill-posed problem due to the loss of motion information in the blur degradation process. Since event cameras can capture apparent motion with a high temporal resolution, several attempts have explored the…

Sound event detection systems are widely used in various applications such as surveillance and environmental monitoring where data is automatically collected, processed, and sent to a cloud for sound recognition. However, this process may…

Personal devices (e.g. laptops, tablets, and mobile phones) are conventional in daily life and have the ability to store users' private data. The security problems related to these appliances have become a primary concern for both users and…

Contemporary Video Instance Segmentation (VIS) methods typically adhere to a pre-train then fine-tune regime, where a segmentation model trained on images is fine-tuned on videos. However, the lack of temporal knowledge in the pre-trained…

As AI advances, copyrighted content faces growing risk of unauthorized use, whether through model training or direct misuse. Building upon invisible adversarial perturbation, recent works developed copyright protections against specific AI…

We introduce a framework that predicts the goals behind observable human action in video. Motivated by evidence in developmental psychology, we leverage video of unintentional action to learn video representations of goals without direct…

While deep neural networks can achieve state-of-the-art performance in many tasks, these models are more fragile than they appear. They are prone to learning spurious correlations in their training data, leading to surprising failure cases.…

The ability to localize and segment objects from unseen classes would open the door to new applications, such as autonomous object learning in active vision. Nonetheless, improving the performance on unseen classes requires additional…

Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data. Yet, in practice, even models learned with privacy guarantees can inadvertently memorize unique training examples or leak…

3D object trackers usually require training on large amounts of annotated data that is expensive and time-consuming to collect. Instead, we propose leveraging vast unlabeled datasets by self-supervised metric learning of 3D object trackers,…

Deep learning based visual trackers entail offline pre-training on large volumes of video datasets with accurate bounding box annotations that are labor-expensive to achieve. We present a new framework to facilitate bounding box annotations…