Related papers: Video Annotator: A framework for efficiently build…
With the rapid accumulation of text data produced by data-driven techniques, the task of extracting "data annotations"--concise, high-quality data summaries from unstructured raw text--has become increasingly important. The recent advances…
Recent progress in reasoning capabilities of Multimodal Large Language Models(MLLMs) has highlighted their potential for performing complex video understanding tasks. However, in the domain of Video Anomaly Detection and Understanding…
Progress in Multiple Object Tracking (MOT) has been historically limited by the size of the available datasets. We present an efficient framework to annotate trajectories and use it to produce a MOT dataset of unprecedented size. In our…
In this work, we propose an efficient Video-Language Alignment (ViLA) network. Our ViLA model addresses both efficient frame sampling and effective cross-modal alignment in a unified way. In our ViLA network, we design a new learnable…
Present-day deep neural networks for video semantic segmentation require a large number of fine-grained pixel-level annotations to achieve the best possible results. Obtaining such annotations, however, is very expensive. On the other hand,…
Training of autonomous driving systems requires extensive datasets with precise annotations to attain robust performance. Human annotations suffer from imperfections, and multiple iterations are often needed to produce high-quality…
In Active Domain Adaptation (ADA), one uses Active Learning (AL) to select a subset of images from the target domain, which are then annotated and used for supervised domain adaptation (DA). Given the large performance gap between…
Machine learning (ML) and artificial intelligence (AI) systems rely heavily on human-annotated data for training and evaluation. A major challenge in this context is the occurrence of annotation errors, as their effects can degrade model…
Vision-language models (VLMs) have recently emerged as a promising paradigm for video anomaly detection (VAD) due to their strong visual reasoning ability and natural language-based explainability. In this paper, we aim to address a key…
Video moment retrieval aims at finding the start and end timestamps of a moment (part of a video) described by a given natural language query. Fully supervised methods need complete temporal boundary annotations to achieve promising…
The quality of the data and annotation upper-bounds the quality of a downstream model. While there exist large text corpora and image-text pairs, high-quality video-text data is much harder to collect. First of all, manual labeling is more…
Activity recognition is a challenging problem with many practical applications. In addition to the visual features, recent approaches have benefited from the use of context, e.g., inter-relationships among the activities and objects.…
Dense video captioning, a task of localizing meaningful moments and generating relevant captions for videos, often requires a large, expensive corpus of annotated video segments paired with text. In an effort to minimize the annotation…
The application of cross-dataset training in object detection tasks is complicated because the inconsistency in the category range across datasets transforms fully supervised learning into semi-supervised learning. To address this problem,…
The e-learning community has been producing and using video content for a long time, and in the last years, the advent of MOOCs greatly relied on video recordings of teacher courses. Video annotations are information pieces that can be…
Video matting has traditionally been limited by the lack of high-quality ground-truth data. Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations, which must be composited to background…
Recent years have witnessed the rapid progress of perception algorithms on top of LiDAR, a widely adopted sensor for autonomous driving systems. These LiDAR-based solutions are typically data hungry, requiring a large amount of data to be…
Underwater video monitoring is a promising strategy for assessing marine biodiversity, but the vast volume of uneventful footage makes manual inspection highly impractical. In this work, we explore the use of visual anomaly detection (VAD)…
Video understanding requires not only visual recognition but also complex reasoning. While Vision-Language Models (VLMs) demonstrate impressive capabilities, they typically process videos largely in a single-pass manner with limited support…
Though pre-training vision-language models have demonstrated significant benefits in boosting video-text retrieval performance from large-scale web videos, fine-tuning still plays a critical role with manually annotated clips with start and…