I2V-Adapter: A General Image-to-Video Adapter for Video Diffusion Models

In the rapidly evolving domain of digital content generation, the focus has shifted from text-to-image (T2I) models to more advanced video diffusion models, notably text-to-video (T2V) and image-to-video (I2V). This paper addresses the intricate challenge posed by I2V: converting static images into dynamic, lifelike video sequences while preserving the original image fidelity. Traditional methods typically involve integrating entire images into diffusion processes or using pretrained encoders for cross attention. However, these approaches often necessitate altering the fundamental weights of T2I models, thereby restricting their reusability. We introduce a novel solution, namely I2V-Adapter, designed to overcome such limitations. Our approach preserves the structural integrity of T2I models and their inherent motion modules. The I2V-Adapter operates by processing noised video frames in parallel with the input image, utilizing a lightweight adapter module. This module acts as a bridge, efficiently linking the input to the model's self-attention mechanism, thus maintaining spatial details without requiring structural changes to the T2I model. Moreover, I2V-Adapter requires only a fraction of the parameters of conventional models and ensures compatibility with existing community-driven T2I models and controlling tools. Our experimental results demonstrate I2V-Adapter's capability to produce high-quality video outputs. This performance, coupled with its versatility and reduced need for trainable parameters, represents a substantial advancement in the field of AI-driven video generation, particularly for creative applications.

Hulk: A Universal Knowledge Translator for Human-Centric Tasks

Human-centric perception tasks, e.g., human mesh recovery, pedestrian detection, skeleton-based action recognition, and pose estimation, have wide industrial applications, such as metaverse and sports analysis. There is a recent surge to develop human-centric foundation models that can benefit a broad range of human-centric perception tasks. While many human-centric foundation models have achieved success, most of them only excel in 2D vision tasks or require extensive fine-tuning for practical deployment in real-world scenarios. These limitations severely restrict their usability across various downstream tasks and situations. To tackle these problems, we present Hulk, the first multimodal human-centric generalist model, capable of addressing most of the mainstream tasks simultaneously without task-specific finetuning, covering 2D vision, 3D vision, skeleton-based, and vision-language tasks. The key to achieving this is condensing various task-specific heads into two general heads, one for discrete representations, e.g., languages, and the other for continuous representations, e.g., location coordinates. The outputs of two heads can be further stacked into four distinct input and output modalities. This uniform representation enables Hulk to treat human-centric tasks as modality translation, integrating knowledge across a wide range of tasks. To validate the effectiveness of our proposed method, we conduct comprehensive experiments on 11 benchmarks across 8 human-centric tasks. Experimental results surpass previous methods substantially, demonstrating the superiority of our proposed method. The code will be available on https://github.com/OpenGVLab/HumanBench.

StableVideo: Text-driven Consistency-aware Diffusion Video Editing

Diffusion-based methods can generate realistic images and videos, but they struggle to edit existing objects in a video while preserving their appearance over time. This prevents diffusion models from being applied to natural video editing in practical scenarios. In this paper, we tackle this problem by introducing temporal dependency to existing text-driven diffusion models, which allows them to generate consistent appearance for the edited objects. Specifically, we develop a novel inter-frame propagation mechanism for diffusion video editing, which leverages the concept of layered representations to propagate the appearance information from one frame to the next. We then build up a text-driven video editing framework based on this mechanism, namely StableVideo, which can achieve consistency-aware video editing. Extensive experiments demonstrate the strong editing capability of our approach. Compared with state-of-the-art video editing methods, our approach shows superior qualitative and quantitative results. Our code is available at \href{https://github.com/rese1f/StableVideo}{this https URL}.

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

Recently, integrating video foundation models and large language models to build a video understanding system overcoming the limitations of specific pre-defined vision tasks. Yet, existing systems can only handle videos with very few frames. For long videos, the computation complexity, memory cost, and long-term temporal connection are the remaining challenges. Inspired by Atkinson-Shiffrin memory model, we develop an memory mechanism including a rapidly updated short-term memory and a compact thus sustained long-term memory. We employ tokens in Transformers as the carriers of memory. MovieChat achieves state-of-the-art performace in long video understanding.

Alignment-guided Temporal Attention for Video Action Recognition

Temporal modeling is crucial for various video learning tasks. Most recent approaches employ either factorized (2D+1D) or joint (3D) spatial-temporal operations to extract temporal contexts from the input frames. While the former is more efficient in computation, the latter often obtains better performance. In this paper, we attribute this to a dilemma between the sufficiency and the efficiency of interactions among various positions in different frames. These interactions affect the extraction of task-relevant information shared among frames. To resolve this issue, we prove that frame-by-frame alignments have the potential to increase the mutual information between frame representations, thereby including more task-relevant information to boost effectiveness. Then we propose Alignment-guided Temporal Attention (ATA) to extend 1-dimensional temporal attention with parameter-free patch-level alignments between neighboring frames. It can act as a general plug-in for image backbones to conduct the action recognition task without any model-specific design. Extensive experiments on multiple benchmarks demonstrate the superiority and generality of our module.

Rethinking Minimal Sufficient Representation in Contrastive Learning

Contrastive learning between different views of the data achieves outstanding success in the field of self-supervised representation learning and the learned representations are useful in broad downstream tasks. Since all supervision information for one view comes from the other view, contrastive learning approximately obtains the minimal sufficient representation which contains the shared information and eliminates the non-shared information between views. Considering the diversity of the downstream tasks, it cannot be guaranteed that all task-relevant information is shared between views. Therefore, we assume the non-shared task-relevant information cannot be ignored and theoretically prove that the minimal sufficient representation in contrastive learning is not sufficient for the downstream tasks, which causes performance degradation. This reveals a new problem that the contrastive learning models have the risk of over-fitting to the shared information between views. To alleviate this problem, we propose to increase the mutual information between the representation and input as regularization to approximately introduce more task-relevant information, since we cannot utilize any downstream task information during training. Extensive experiments verify the rationality of our analysis and the effectiveness of our method. It significantly improves the performance of several classic contrastive learning models in downstream tasks. Our code is available at https://github.com/Haoqing-Wang/InfoCL.

Semantic-aligned Fusion Transformer for One-shot Object Detection

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 performances are often unsatisfactory. In this paper, we attribute this to inappropriate correlation methods that misalign query-support semantics by overlooking spatial structures and scale variances. Upon analysis, we leverage the attention mechanism and propose a simple but effective architecture named Semantic-aligned Fusion Transformer (SaFT) to resolve these issues. Specifically, we equip SaFT with a vertical fusion module (VFM) for cross-scale semantic enhancement and a horizontal fusion module (HFM) for cross-sample feature fusion. Together, they broaden the vision for each feature point from the support to a whole augmented feature pyramid from the query, facilitating semantic-aligned associations. Extensive experiments on multiple benchmarks demonstrate the superiority of our framework. Without fine-tuning on novel classes, it brings significant performance gains to one-stage baselines, lifting state-of-the-art results to a higher level.

Self-Supervised Video Representation Learning with Meta-Contrastive Network

Self-supervised learning has been successfully applied to pre-train video representations, which aims at efficient adaptation from pre-training domain to downstream tasks. Existing approaches merely leverage contrastive loss to learn instance-level discrimination. However, lack of category information will lead to hard-positive problem that constrains the generalization ability of this kind of methods. We find that the multi-task process of meta learning can provide a solution to this problem. In this paper, we propose a Meta-Contrastive Network (MCN), which combines the contrastive learning and meta learning, to enhance the learning ability of existing self-supervised approaches. Our method contains two training stages based on model-agnostic meta learning (MAML), each of which consists of a contrastive branch and a meta branch. Extensive evaluations demonstrate the effectiveness of our method. For two downstream tasks, i.e., video action recognition and video retrieval, MCN outperforms state-of-the-art approaches on UCF101 and HMDB51 datasets. To be more specific, with R(2+1)D backbone, MCN achieves Top-1 accuracies of 84.8% and 54.5% for video action recognition, as well as 52.5% and 23.7% for video retrieval.