Image cropping aims to find visually appealing crops in an image, which is an important yet challenging task. In this paper, we consider a specific and practical application: human-centric image cropping, which focuses on the depiction of a person. To this end, we propose a human-centric image cropping method with two novel feature designs for the candidate crop: partition-aware feature and content-preserving feature. For partition-aware feature, we divide the whole image into nine partitions based on the human bounding box and treat different partitions in a candidate crop differently conditioned on the human information. For content-preserving feature, we predict a heatmap indicating the important content to be included in a good crop, and extract the geometric relation between the heatmap and a candidate crop. Extensive experiments demonstrate that our method can perform favorably against state-of-the-art image cropping methods on human-centric image cropping task. Code is available at https://github.com/bcmi/Human-Centric-Image-Cropping.
When using cut-and-paste to acquire a composite image, the geometry inconsistency between foreground and background may severely harm its fidelity. To address the geometry inconsistency in composite images, several existing works learned to warp the foreground object for geometric correction. However, the absence of annotated dataset results in unsatisfactory performance and unreliable evaluation. In this work, we contribute a Spatial TRAnsformation for virtual Try-on (STRAT) dataset covering three typical application scenarios. Moreover, previous works simply concatenate foreground and background as input without considering their mutual correspondence. Instead, we propose a novel correspondence learning network (CorrelNet) to model the correspondence between foreground and background using cross-attention maps, based on which we can predict the target coordinate that each source coordinate of foreground should be mapped to on the background. Then, the warping parameters of foreground object can be derived from pairs of source and target coordinates. Additionally, we learn a filtering mask to eliminate noisy pairs of coordinates to estimate more accurate warping parameters. Extensive experiments on our STRAT dataset demonstrate that our proposed CorrelNet performs more favorably against previous methods.
Video understanding has achieved great success in representation learning, such as video caption, video object grounding, and video descriptive question-answer. However, current methods still struggle on video reasoning, including evidence reasoning and commonsense reasoning. To facilitate deeper video understanding towards video reasoning, we present the task of Causal-VidQA, which includes four types of questions ranging from scene description (description) to evidence reasoning (explanation) and commonsense reasoning (prediction and counterfactual). For commonsense reasoning, we set up a two-step solution by answering the question and providing a proper reason. Through extensive experiments on existing VideoQA methods, we find that the state-of-the-art methods are strong in descriptions but weak in reasoning. We hope that Causal-VidQA can guide the research of video understanding from representation learning to deeper reasoning. The dataset and related resources are available at \url{https://github.com/bcmi/Causal-VidQA.git}.
Video harmonization aims to adjust the foreground of a composite video to make it compatible with the background. So far, video harmonization has only received limited attention and there is no public dataset for video harmonization. In this work, we construct a new video harmonization dataset HYouTube by adjusting the foreground of real videos to create synthetic composite videos. Moreover, we consider the temporal consistency in video harmonization task. Unlike previous works which establish the spatial correspondence, we design a novel framework based on the assumption of color mapping consistency, which leverages the color mapping of neighboring frames to refine the current frame. Extensive experiments on our HYouTube dataset prove the effectiveness of our proposed framework. Our dataset and code are available at https://github.com/bcmi/Video-Harmonization-Dataset-HYouTube.
Recently, various multimodal networks for Visually-Rich Document Understanding(VRDU) have been proposed, showing the promotion of transformers by integrating visual and layout information with the text embeddings. However, most existing approaches utilize the position embeddings to incorporate the sequence information, neglecting the noisy improper reading order obtained by OCR tools. In this paper, we propose a robust layout-aware multimodal network named XYLayoutLM to capture and leverage rich layout information from proper reading orders produced by our Augmented XY Cut. Moreover, a Dilated Conditional Position Encoding module is proposed to deal with the input sequence of variable lengths, and it additionally extracts local layout information from both textual and visual modalities while generating position embeddings. Experiment results show that our XYLayoutLM achieves competitive results on document understanding tasks.
Video Instance Segmentation (VIS) is a task that simultaneously requires classification, segmentation, and instance association in a video. Recent VIS approaches rely on sophisticated pipelines to achieve this goal, including RoI-related operations or 3D convolutions. In contrast, we present a simple and efficient single-stage VIS framework based on the instance segmentation method CondInst by adding an extra tracking head. To improve instance association accuracy, a novel bi-directional spatio-temporal contrastive learning strategy for tracking embedding across frames is proposed. Moreover, an instance-wise temporal consistency scheme is utilized to produce temporally coherent results. Experiments conducted on the YouTube-VIS-2019, YouTube-VIS-2021, and OVIS-2021 datasets validate the effectiveness and efficiency of the proposed method. We hope the proposed framework can serve as a simple and strong alternative for many other instance-level video association tasks. Code will be made available.
Object detection has achieved promising success, but requires large-scale fully-annotated data, which is time-consuming and labor-extensive. Therefore, we consider object detection with mixed supervision, which learns novel object categories using weak annotations with the help of full annotations of existing base object categories. Previous works using mixed supervision mainly learn the class-agnostic objectness from fully-annotated categories, which can be transferred to upgrade the weak annotations to pseudo full annotations for novel categories. In this paper, we further transfer mask prior and semantic similarity to bridge the gap between novel categories and base categories. Specifically, the ability of using mask prior to help detect objects is learned from base categories and transferred to novel categories. Moreover, the semantic similarity between objects learned from base categories is transferred to denoise the pseudo full annotations for novel categories. Experimental results on three benchmark datasets demonstrate the effectiveness of our method over existing methods. Codes are available at https://github.com/bcmi/TraMaS-Weak-Shot-Object-Detection.
Weakly-supervised semantic segmentation (WSSS) with image-level labels has been widely studied to relieve the annotation burden of the traditional segmentation task. In this paper, we show that existing fully-annotated base categories can help segment objects of novel categories with only image-level labels, even if base and novel categories have no overlap. We refer to this task as weak-shot semantic segmentation, which could also be treated as WSSS with auxiliary fully-annotated categories. Recent advanced WSSS methods usually obtain class activation maps (CAMs) and refine them by affinity propagation. Based on the observation that semantic affinity and boundary are class-agnostic, we propose a method under the WSSS framework to transfer semantic affinity and boundary from base categories to novel ones. As a result, we find that pixel-level annotation of base categories can facilitate affinity learning and propagation, leading to higher-quality CAMs of novel categories. Extensive experiments on PASCAL VOC 2012 dataset demonstrate that our method significantly outperforms WSSS baselines on novel categories.
Video composition aims to generate a composite video by combining the foreground of one video with the background of another video, but the inserted foreground may be incompatible with the background in terms of color and illumination. Video harmonization aims to adjust the foreground of a composite video to make it compatible with the background. So far, video harmonization has only received limited attention and there is no public dataset for video harmonization. In this work, we construct a new video harmonization dataset HYouTube by adjusting the foreground of real videos to create synthetic composite videos. Considering the domain gap between real composite videos and synthetic composite videos, we additionally create 100 real composite videos via copy-and-paste. Datasets are available at https://github.com/bcmi/Video-Harmonization-Dataset-HYouTube.