Related papers: FOAM: A General Frequency-Optimized Anti-Overlappi…
This paper proposes a knowledge distillation method for foreground object search (FoS). Given a background and a rectangle specifying the foreground location and scale, FoS retrieves compatible foregrounds in a certain category for later…
Object-level mapping builds a 3D map of objects in a scene with detailed shapes and poses from multi-view sensor observations. Conventional methods struggle to build complete shapes and estimate accurate poses due to partial occlusions and…
The infrared and visible images fusion (IVIF) is receiving increasing attention from both the research community and industry due to its excellent results in downstream applications. Existing deep learning approaches often utilize…
Dense image prediction tasks demand features with strong category information and precise spatial boundary details at high resolution. To achieve this, modern hierarchical models often utilize feature fusion, directly adding upsampled…
Sequential DeepFake detection is an emerging task that predicts the manipulation sequence in order. Existing methods typically formulate it as an image-to-sequence problem, employing conventional Transformer architectures. However, these…
Various deepfake detectors have been proposed, but challenges still exist to detect images of unknown categories or GAN models outside of the training settings. Such issues arise from the overfitting issue, which we discover from our own…
Detecting 3D objects accurately from multi-view 2D images is a challenging yet essential task in the field of autonomous driving. Current methods resort to integrating depth prediction to recover the spatial information for object query…
Spatiotemporal fusion aims to improve both the spatial and temporal resolution of remote sensing images, thus facilitating time-series analysis at a fine spatial scale. However, there are several important issues that limit the application…
Existing camouflage object detection (COD) methods typically rely on fully-supervised learning guided by mask annotations. However, obtaining mask annotations is time-consuming and labor-intensive. Compared to fully-supervised methods,…
Collaborative perception has the potential to significantly enhance perceptual accuracy through the sharing of complementary information among agents. However, real-world collaborative perception faces persistent challenges, particularly in…
Contrastive self-supervised learning has shown impressive results in learning visual representations from unlabeled images by enforcing invariance against different data augmentations. However, the learned representations are often…
The primary challenge in Video Object Detection (VOD) is effectively exploiting temporal information to enhance object representations. Traditional strategies, such as aggregating region proposals, often suffer from feature variance due to…
The prediction of formation resistivity plays a crucial role in the evaluation of oil and gas reservoirs, identification and assessment of geothermal energy resources, groundwater detection and monitoring, and carbon capture and storage.…
Consecutive frames in a video contain redundancy, but they may also contain relevant complementary information for the detection task. The objective of our work is to leverage this complementary information to improve detection. Therefore,…
Source-Free Object Detection (SFOD) aims to adapt a source-pretrained object detector to a target domain without access to source data. However, existing SFOD methods predominantly rely on internal knowledge from the source model, which…
Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial perturbation (UAP)…
In recent years, object-oriented simultaneous localization and mapping (SLAM) has attracted increasing attention due to its ability to provide high-level semantic information while maintaining computational efficiency. Some researchers have…
Image fusion aims to integrate complementary information across modalities to generate high-quality fused images, thereby enhancing the performance of high-level vision tasks. While global spatial modeling mechanisms show promising results,…
We introduce FOF-X for real-time reconstruction of detailed human geometry from a single image. Balancing real-time speed against high-quality results is a persistent challenge, mainly due to the high computational demands of existing 3D…
Multispectral images (e.g. visible and infrared) may be particularly useful when detecting objects with the same model in different environments (e.g. day/night outdoor scenes). To effectively use the different spectra, the main technical…