相关论文: Cross-Video Contextual Knowledge Exploration and E…

Weakly supervised object localization (WSOL) focuses on localizing objects only with the supervision of image-level classification masks. Most previous WSOL methods follow the classification activation map (CAM) that localizes objects based…

Text-video retrieval aims to find the most semantically similar videos with given text queries. However, since videos contain more diverse content than texts, the main semantics expressed by each text-video pair is often partially relevant.…

Transcription-only Supervised Text Spotting aims to learn text spotters relying only on transcriptions but no text boundaries for supervision, thus eliminating expensive boundary annotation. The crux of this task lies in locating each…

Temporal Action Localization (TAL) involves localizing and classifying action snippets in an untrimmed video. The emergence of large video foundation models has led RGB-only video backbones to outperform previous methods needing both RGB…

Generalized Category Discovery (GCD) is an emerging and challenging open-world problem that has garnered increasing attention in recent years. Most existing GCD methods focus on discovering categories in static images. However, relying…

Temporal action segmentation is a topic of increasing interest, however, annotating each frame in a video is cumbersome and costly. Weakly supervised approaches therefore aim at learning temporal action segmentation from videos that are…

Automatic surgical scene segmentation is fundamental for facilitating cognitive intelligence in the modern operating theatre. Previous works rely on conventional aggregation modules (e.g., dilated convolution, convolutional LSTM), which…

Weakly supervised video anomaly detection (WSVAD) is a challenging task since only video-level labels are available for training. In previous studies, the discriminative power of the learned features is not strong enough, and the data…

Scarcity of pixel-level labels is a significant challenge in practical scenarios. In specific domains like industrial smoke, acquiring such detailed annotations is particularly difficult and often requires expert knowledge. To alleviate…

Though adversarial erasing has prevailed in weakly supervised semantic segmentation to help activate integral object regions, existing approaches still suffer from the dilemma of under-activation and over-expansion due to the difficulty in…

Compared with tedious per-pixel mask annotating, it is much easier to annotate data by clicks, which costs only several seconds for an image. However, applying clicks to learn video semantic segmentation model has not been explored before.…

Learning to localize actions in long, cluttered, and untrimmed videos is a hard task, that in the literature has typically been addressed assuming the availability of large amounts of annotated training samples for each class -- either in a…

High-quality video datasets are foundational for training robust models in tasks like action recognition, phase detection, and event segmentation. However, many real-world video datasets suffer from annotation errors such as *mislabeling*,…

In industrial settings, weakly supervised (WS) methods are usually preferred over their fully supervised (FS) counterparts as they do not require costly manual annotations. Unfortunately, the segmentation masks obtained in the WS regime are…

Universal models for medical image segmentation, such as interactive and in-context learning (ICL) models, offer strong generalization but require extensive annotations. Interactive models need repeated user prompts for each image, while…

Vision-language models such as CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions due to pre-training on short and concise captions. We present FAST-GOAL…

Video transformers have recently emerged as a competitive alternative to 3D CNNs for video understanding. However, due to their large number of parameters and reduced inductive biases, these models require supervised pretraining on…

Long-form video understanding requires designing approaches that are able to temporally localize activities or language. End-to-end training for such tasks is limited by the compute device memory constraints and lack of temporal annotations…

Temporal cues in videos provide important information for recognizing actions accurately. However, temporal-discriminative features can hardly be extracted without using an annotated large-scale video action dataset for training. This paper…

The task of language-guided video temporal grounding is to localize the particular video clip corresponding to a query sentence in an untrimmed video. Though progress has been made continuously in this field, some issues still need to be…