Related papers: Change Captioning in Remote Sensing: Evolution to …
Remote sensing is critical for disaster monitoring, yet existing datasets lack temporal image pairs and detailed textual annotations. While single-snapshot imagery dominates current resources, it fails to capture dynamic disaster impacts…
Scene understanding is crucial for autonomous robots in dynamic environments for making future state predictions, avoiding collisions, and path planning. Camera and LiDAR perception made tremendous progress in recent years, but face…
Object detection in Remote Sensing Images (RSI) is a critical task for numerous applications in Earth Observation (EO). Differing from object detection in natural images, object detection in remote sensing images faces challenges of…
Person re-identification (ReID) has recently benefited from large pretrained vision-language models such as Contrastive Language-Image Pre-Training (CLIP). However, the absence of concrete descriptions necessitates the use of implicit text…
One-shot object detection aims at detecting novel objects according to merely one given instance. With extreme data scarcity, current approaches explore various feature fusions to obtain directly transferable meta-knowledge. Yet, their…
Change detection (CD) is a fundamental task in remote sensing (RS) which aims to detect the semantic changes between the same geographical regions at different time stamps. Existing convolutional neural networks (CNNs) based approaches…
Referring Remote Sensing Image Segmentation provides a flexible and fine-grained framework for remote sensing scene analysis via vision-language collaborative interpretation. Current approaches predominantly utilize a three-stage pipeline…
Video Captioning (VC) is a challenging multi-modal task since it requires describing the scene in language by understanding various and complex videos. For machines, the traditional VC follows the…
Image Captioning is a fundamental task to join vision and language, concerning about cross-modal understanding and text generation. Recent years witness the emerging attention on image captioning. Most of existing works follow a traditional…
Remote sensing change detection is essential for environmental monitoring, urban planning, and related applications. However, current methods often struggle to capture long-range dependencies while maintaining computational efficiency.…
Recent neural models for image captioning usually employ an encoder-decoder framework with an attention mechanism. However, the attention mechanism in such a framework aligns one single (attended) image feature vector to one caption word,…
While automated audio captioning (AAC) has made notable progress, traditional fully supervised AAC models still face two critical challenges: the need for expensive audio-text pair data for training and performance degradation when…
While advanced image captioning systems are increasingly describing images coherently and exactly, recent progress in continual learning allows deep learning models to avoid catastrophic forgetting. However, the domain where image…
Synthetic aperture radar (SAR) image change detection is a critical yet challenging task in the field of remote sensing image analysis. The task is non-trivial due to the following challenges: Firstly, intrinsic speckle noise of SAR images…
Visual captioning aims to generate textual descriptions given images or videos. Traditionally, image captioning models are trained on human annotated datasets such as Flickr30k and MS-COCO, which are limited in size and diversity. This…
For change detection in remote sensing, constructing a training dataset for deep learning models is difficult due to the requirements of bi-temporal supervision. To overcome this issue, single-temporal supervision which treats change labels…
Remote-sensing (RS) Change Detection (CD) aims to detect "changes of interest" from co-registered bi-temporal images. The performance of existing deep supervised CD methods is attributed to the large amounts of annotated data used to train…
As the most critical components in a sentence, subject, predicate and object require special attention in the video captioning task. To implement this idea, we design a novel framework, named COllaborative three-Stream Transformers (COST),…
We present CAT-V (Caption AnyThing in Video), a training-free framework for fine-grained object-centric video captioning that enables detailed descriptions of user-selected objects through time. CAT-V integrates three key components: a…
Synthetic Aperture Radar (SAR) image captioning enables scene-level semantic understanding and plays a crucial role in applications such as military intelligence and urban planning, but its development is limited by the scarcity of…