Related papers: Live or Lie: Action-Aware Capsule Multiple Instanc…
Multi-instance learning (MIL) is widely used in the computer-aided interpretation of pathological Whole Slide Images (WSIs) to solve the lack of pixel-wise or patch-wise annotations. Often, this approach directly applies "natural image…
Multiple instance learning (MIL) has emerged as the dominant paradigm for whole slide image (WSI) analysis in computational pathology, achieving strong diagnostic performance through patch-level feature aggregation. However, existing MIL…
Temporal Action Localization (TAL) aims to predict both action category and temporal boundary of action instances in untrimmed videos, i.e., start and end time. Fully-supervised solutions are usually adopted in most existing works, and…
Multiple Instance Learning (MIL) offers a natural solution for settings where only coarse, bag-level labels are available, without having access to instance-level annotations. This is usually the case in digital pathology, which consists of…
A new multi-attention based method for solving the MIL problem (MAMIL), which takes into account the neighboring patches or instances of each analyzed patch in a bag, is proposed. In the method, one of the attention modules takes into…
Social video anomaly is an observation in video streams that does not conform to a common pattern of dataset's behaviour. Social video anomaly detection plays a critical role in applications from e-commerce to e-learning. Traditionally,…
Many previous audio-visual voice-related works focus on speech, ignoring the singing voice in the growing number of musical video streams on the Internet. For processing diverse musical video data, voice activity detection is a necessary…
In Multiple Instance Learning (MIL), models are trained using bags of instances, where only a single label is provided for each bag. A bag label is often only determined by a handful of key instances within a bag, making it difficult to…
Active learning has proven to be useful for minimizing labeling costs by selecting the most informative samples. However, existing active learning methods do not work well in realistic scenarios such as imbalance or rare classes,…
It is significantly challenging to recognize daily human actions in homes due to the diversity and dynamic changes in unconstrained home environments. It spurs the need to continually adapt to various users and scenes. Fine-tuning current…
Classifying pill categories from real-world images is crucial for various smart healthcare applications. Although existing approaches in image classification might achieve a good performance on fixed pill categories, they fail to handle…
The development of multimodal large language models (MLLMs) has advanced general video understanding. However, existing video evaluation benchmarks primarily focus on non-interactive videos, such as movies and recordings. To fill this gap,…
This work addresses the problem of Social Activity Recognition (SAR), a critical component in real-world tasks like surveillance and assistive robotics. Unlike traditional event understanding approaches, SAR necessitates modeling individual…
The canonical approach to video action recognition dictates a neural model to do a classic and standard 1-of-N majority vote task. They are trained to predict a fixed set of predefined categories, limiting their transferable ability on new…
Attention-based multiple instance learning (AMIL) algorithms have proven to be successful in utilizing gigapixel whole-slide images (WSIs) for a variety of different computational pathology tasks such as outcome prediction and cancer…
The proliferation of automated data collection schemes and the advances in sensorics are increasing the amount of data we are able to monitor in real-time. However, given the high annotation costs and the time required by quality…
Action anticipation, the task of predicting future actions from partially observed videos, is crucial for advancing intelligent systems. Unlike action recognition, which operates on fully observed videos, action anticipation must handle…
We study a multiclass multiple instance learning (MIL) problem where the labels only suggest whether any instance of a class exists or does not exist in a training sample or example. No further information, e.g., the number of instances of…
Temporal action localization (TAL), which involves recognizing and locating action instances, is a challenging task in video understanding. Most existing approaches directly predict action classes and regress offsets to boundaries, while…
With the rapid development of the Internet, users have increasingly higher expectations for the recommendation accuracy of online content consumption platforms. However, short videos often contain diverse segments, and users may not hold…