From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering

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}.

Deep Video Harmonization with Color Mapping Consistency

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.

XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding

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.

STC: Spatio-Temporal Contrastive Learning for Video Instance Segmentation

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.

Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity

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.

Weak-shot Semantic Segmentation by Transferring Semantic Affinity and Boundary

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.

HYouTube: Video Harmonization Dataset

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.

High-Resolution Image Harmonization via Collaborative Dual Transformations

Given a composite image, image harmonization aims to adjust the foreground to make it compatible with the background. High-resolution image harmonization is in high demand, but still remains unexplored. Conventional image harmonization methods learn global RGB-to-RGB transformation which could effortlessly scale to high resolution, but ignore diverse local context. Recent deep learning methods learn the dense pixel-to-pixel transformation which could generate harmonious outputs, but are highly constrained in low resolution. In this work, we propose a high-resolution image harmonization network with Collaborative Dual Transformation (CDTNet) to combine pixel-to-pixel transformation and RGB-to-RGB transformation coherently in an end-to-end framework. Our CDTNet consists of a low-resolution generator for pixel-to-pixel transformation, a color mapping module for RGB-to-RGB transformation, and a refinement module to take advantage of both. Extensive experiments on high-resolution image harmonization dataset demonstrate that our CDTNet strikes a good balance between efficiency and effectiveness.

Visible Watermark Removal via Self-calibrated Localization and Background Refinement

Superimposing visible watermarks on images provides a powerful weapon to cope with the copyright issue. Watermark removal techniques, which can strengthen the robustness of visible watermarks in an adversarial way, have attracted increasing research interest. Modern watermark removal methods perform watermark localization and background restoration simultaneously, which could be viewed as a multi-task learning problem. However, existing approaches suffer from incomplete detected watermark and degraded texture quality of restored background. Therefore, we design a two-stage multi-task network to address the above issues. The coarse stage consists of a watermark branch and a background branch, in which the watermark branch self-calibrates the roughly estimated mask and passes the calibrated mask to background branch to reconstruct the watermarked area. In the refinement stage, we integrate multi-level features to improve the texture quality of watermarked area. Extensive experiments on two datasets demonstrate the effectiveness of our proposed method.

Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer

Vision transformers have recently received explosive popularity, but the huge computational cost is still a severe issue. Recent efficient designs for vision transformers follow two pipelines, namely, structural compression based on local spatial prior and non-structural token pruning. However, token pruning breaks the spatial structure that is indispensable for local spatial prior. To take advantage of both two pipelines, this work seeks to dynamically identify uninformative tokens for each instance and trim down both the training and inference complexity while maintaining complete spatial structure and information flow. To achieve this goal, we propose Evo-ViT, a self-motivated slow-fast token evolution method for vision transformers. Specifically, we conduct unstructured instance-wise token selection by taking advantage of the global class attention that is unique to vision transformers. Then, we propose to update informative tokens and placeholder tokens that contribute little to the final prediction with different computational priorities, namely, slow-fast updating. Thanks to the slow-fast updating mechanism that guarantees information flow and spatial structure, our Evo-ViT can accelerate vanilla transformers of both flat and deep-narrow structures from the very beginning of the training process. Experimental results demonstrate that the proposed method can significantly reduce the computational costs of vision transformers while maintaining comparable performance on image classification. For example, our method accelerates DeiTS by over 60% throughput while only sacrificing 0.4% top-1 accuracy.