Hongjie Zhang

Yi Wang, Kunchang Li, Yizhuo Li et al.

The foundation models have recently shown excellent performance on a variety of downstream tasks in computer vision. However, most existing vision foundation models simply focus on image-level pretraining and adpation, which are limited for dynamic and complex video-level understanding tasks. To fill the gap, we present general video foundation models, InternVideo, by taking advantage of both generative and discriminative self-supervised video learning. Specifically, InternVideo efficiently explores masked video modeling and video-language contrastive learning as the pretraining objectives, and selectively coordinates video representations of these two complementary frameworks in a learnable manner to boost various video applications. Without bells and whistles, InternVideo achieves state-of-the-art performance on 39 video datasets from extensive tasks including video action recognition/detection, video-language alignment, and open-world video applications. Especially, our methods can obtain 91.1% and 77.2% top-1 accuracy on the challenging Kinetics-400 and Something-Something V2 benchmarks, respectively. All of these results effectively show the generality of our InternVideo for video understanding. The code will be released at https://github.com/OpenGVLab/InternVideo .

Guo Chen, Sen Xing, Zhe Chen et al.

In this report, we present our champion solutions to five tracks at Ego4D challenge. We leverage our developed InternVideo, a video foundation model, for five Ego4D tasks, including Moment Queries, Natural Language Queries, Future Hand Prediction, State Change Object Detection, and Short-term Object Interaction Anticipation. InternVideo-Ego4D is an effective paradigm to adapt the strong foundation model to the downstream ego-centric video understanding tasks with simple head designs. In these five tasks, the performance of InternVideo-Ego4D comprehensively surpasses the baseline methods and the champions of CVPR2022, demonstrating the powerful representation ability of InternVideo as a video foundation model. Our code will be released at https://github.com/OpenGVLab/ego4d-eccv2022-solutions

Yi Wang, Kunchang Li, Xinhao Li et al.

We introduce InternVideo2, a new family of video foundation models (ViFM) that achieve the state-of-the-art results in video recognition, video-text tasks, and video-centric dialogue. Our core design is a progressive training approach that unifies the masked video modeling, crossmodal contrastive learning, and next token prediction, scaling up the video encoder size to 6B parameters. At the data level, we prioritize spatiotemporal consistency by semantically segmenting videos and generating video-audio-speech captions. This improves the alignment between video and text. Through extensive experiments, we validate our designs and demonstrate superior performance on over 60 video and audio tasks. Notably, our model outperforms others on various video-related dialogue and long video understanding benchmarks, highlighting its ability to reason and comprehend longer contexts. Code and models are available at https://github.com/OpenGVLab/InternVideo/tree/main/InternVideo2/.

Hongjie Zhang, Lu Dong, Yi Liu et al.

Despite remarkable recent progress, existing long-form VideoQA datasets fall short of meeting the criteria for genuine long-form video understanding. This is primarily due to the use of short videos for question curation, and the reliance on limited-length sub-clips as clues to answer those questions. Meanwhile, previous datasets have limited focus on question type and modality. To remedy this, we introduce LvBench, a Long-form video understanding benchmark for versatile multi-modal question-answering. Our LvBench stands out from existing long-form VideoQA datasets through three key characteristics: 1) Extended temporal durations: We consider videos ranging from 70 seconds to 4 hours, covering single-scene, multi-scene, and full-scene contexts. This design accounts for both video and clue lengths, capturing diverse contextual dynamics. 2) Diverse question types and modalities: LvBench introduces six distinct question types that evaluate various perceptual and cognitive capabilities, utilizing both video frames and subtitles. 3) High-quality annotations: We employ rigorous manual labeling by human annotators. Our dataset comprises 20,061 question-answer pairs sourced from 100 carefully selected movies across diverse genres, annotated collaboratively by multiple individuals. Analysis involving various baselines reveals a consistent trend: the performance of all existing methods significantly deteriorates when video and clue length increases. We expect LvBench to serve as a valuable resource for future works on long-form video understanding.

Hongjie Zhang

Feature extraction is an efficient approach for alleviating the issue of dimensionality in high-dimensional data. As a popular self-supervised learning method, contrastive learning has recently garnered considerable attention. In this study, we proposed a unified framework based on a new perspective of contrastive learning (CL) that is suitable for both unsupervised and supervised feature extraction. The proposed framework first constructed two CL graph for uniquely defining the positive and negative pairs. Subsequently, the projection matrix was determined by minimizing the contrastive loss function. In addition, the proposed framework considered both similar and dissimilar samples to unify unsupervised and supervised feature extraction. Moreover, we propose the three specific methods: unsupervised contrastive learning method, supervised contrastive learning method 1 ,and supervised contrastive learning method 2. Finally, the numerical experiments on five real datasets demonstrated the superior performance of the proposed framework in comparison to the existing methods.

Jingwu He, Linbo Wang, Wenzhe Zhou et al.

This paper studies the problem of how to choose good viewpoints for taking photographs of architectures. We achieve this by learning from professional photographs of world famous landmarks that are available on the Internet. Unlike previous efforts devoted to photo quality assessment which mainly rely on 2D image features, we show in this paper combining 2D image features extracted from images with 3D geometric features computed on the 3D models can result in more reliable evaluation of viewpoint quality. Specifically, we collect a set of photographs for each of 15 world famous architectures as well as their 3D models from the Internet. Viewpoint recovery for images is carried out through an image-model registration process, after which a newly proposed viewpoint clustering strategy is exploited to validate users' viewpoint preferences when photographing landmarks. Finally, we extract a number of 2D and 3D features for each image based on multiple visual and geometric cues and perform viewpoint recommendation by learning from both 2D and 3D features using a specifically designed SVM-2K multi-view learner, achieving superior performance over using solely 2D or 3D features. We show the effectiveness of the proposed approach through extensive experiments. The experiments also demonstrate that our system can be used to recommend viewpoints for rendering textured 3D models of buildings for the use of architectural design, in addition to viewpoint evaluation of photographs and recommendation of viewpoints for photographing architectures in practice.