The increasing variety and quantity of tagged multimedia content on platforms such as TikTok provides an opportunity to advance computer vision modeling. We have curated a distinctive dataset of 283,582 unique video clips categorized under 386 hashtags relating to modern human actions. We release this dataset as a valuable resource for building domain-specific foundation models for human movement modeling tasks such as action recognition. To validate this dataset, which we name TikTokActions, we perform two sets of experiments. First, we pretrain the state-of-the-art VideoMAEv2 with a ViT-base backbone on TikTokActions subset, and then fine-tune and evaluate on popular datasets such as UCF101 and the HMDB51. We find that the performance of the model pre-trained using our Tik-Tok dataset is comparable to models trained on larger action recognition datasets (95.3% on UCF101 and 53.24% on HMDB51). Furthermore, our investigation into the relationship between pre-training dataset size and fine-tuning performance reveals that beyond a certain threshold, the incremental benefit of larger training sets diminishes. This work introduces a useful TikTok video dataset that is available for public use and provides insights into the marginal benefit of increasing pre-training dataset sizes for video-based foundation models.
相關內容
Current approaches for 3D human motion synthesis generate high-quality animations of digital humans performing a wide variety of actions and gestures. However, a notable technological gap exists in addressing the complex dynamics of multi-human interactions within this paradigm. In this work, we present ReMoS, a denoising diffusion-based model that synthesizes full-body reactive motion of a person in a two-person interaction scenario. Assuming the motion of one person is given, we employ a combined spatio-temporal cross-attention mechanism to synthesize the reactive body and hand motion of the second person, thereby completing the interactions between the two. We demonstrate ReMoS across challenging two-person scenarios such as pair-dancing, Ninjutsu, kickboxing, and acrobatics, where one person's movements have complex and diverse influences on the other. We also contribute the ReMoCap dataset for two-person interactions containing full-body and finger motions. We evaluate ReMoS through multiple quantitative metrics, qualitative visualizations, and a user study, and also indicate usability in interactive motion editing applications.
Recently, significant progress has been achieved in sensing real large-scale outdoor 3D environments, particularly by using modern acquisition equipment such as LiDAR sensors. Unfortunately, they are fundamentally limited in their ability to produce dense, complete 3D scenes. To address this issue, recent learning-based methods integrate neural implicit representations and optimizable feature grids to approximate surfaces of 3D scenes. However, naively fitting samples along raw LiDAR rays leads to noisy 3D mapping results due to the nature of sparse, conflicting LiDAR measurements. Instead, in this work we depart from fitting LiDAR data exactly, instead letting the network optimize a non-metric monotonic implicit field defined in 3D space. To fit our field, we design a learning system integrating a monotonicity loss that enables optimizing neural monotonic fields and leverages recent progress in large-scale 3D mapping. Our algorithm achieves high-quality dense 3D mapping performance as captured by multiple quantitative and perceptual measures and visual results obtained for Mai City, Newer College, and KITTI benchmarks. The code of our approach will be made publicly available.
Over-correction is a critical problem in Chinese grammatical error correction (CGEC) task. Recent work using model ensemble methods based on voting can effectively mitigate over-correction and improve the precision of the GEC system. However, these methods still require the output of several GEC systems and inevitably lead to reduced error recall. In this light, we propose the LM-Combiner, a rewriting model that can directly modify the over-correction of GEC system outputs without a model ensemble. Specifically, we train the model on an over-correction dataset constructed through the proposed K-fold cross inference method, which allows it to directly generate filtered sentences by combining the original and the over-corrected text. In the inference stage, we directly take the original sentences and the output results of other systems as input and then obtain the filtered sentences through LM-Combiner. Experiments on the FCGEC dataset show that our proposed method effectively alleviates the over-correction of the original system (+18.2 Precision) while ensuring the error recall remains unchanged. Besides, we find that LM-Combiner still has a good rewriting performance even with small parameters and few training data, and thus can cost-effectively mitigate the over-correction of black-box GEC systems (e.g., ChatGPT).
We propose FocusCLIP, integrating subject-level guidance--a specialized mechanism for target-specific supervision--into the CLIP framework for improved zero-shot transfer on human-centric tasks. Our novel contributions enhance CLIP on both the vision and text sides. On the vision side, we incorporate ROI heatmaps emulating human visual attention mechanisms to emphasize subject-relevant image regions. On the text side, we introduce human pose descriptions to provide rich contextual information. For human-centric tasks, FocusCLIP is trained with images from the MPII Human Pose dataset. The proposed approach surpassed CLIP by an average of 8.61% across five previously unseen datasets covering three human-centric tasks. FocusCLIP achieved an average accuracy of 33.65% compared to 25.04% by CLIP. We observed a 3.98% improvement in activity recognition, a 14.78% improvement in age classification, and a 7.06% improvement in emotion recognition. Moreover, using our proposed single-shot LLM prompting strategy, we release a high-quality MPII Pose Descriptions dataset to encourage further research in multimodal learning for human-centric tasks. Furthermore, we also demonstrate the effectiveness of our subject-level supervision on non-human-centric tasks. FocusCLIP shows a 2.47% improvement over CLIP in zero-shot bird classification using the CUB dataset. Our findings emphasize the potential of integrating subject-level guidance with general pretraining methods for enhanced downstream performance.
This work tackles the challenging task of achieving real-time novel view synthesis on various scenes, including highly reflective objects and unbounded outdoor scenes. Existing real-time rendering methods, especially those based on meshes, often have subpar performance in modeling surfaces with rich view-dependent appearances. Our key idea lies in leveraging meshes for rendering acceleration while incorporating a novel approach to parameterize view-dependent information. We decompose the color into diffuse and specular, and model the specular color in the reflected direction based on a neural environment map. Our experiments demonstrate that our method achieves comparable reconstruction quality for highly reflective surfaces compared to state-of-the-art offline methods, while also efficiently enabling real-time rendering on edge devices such as smartphones.
We introduce InternVideo2, a new video foundation model (ViFM) that achieves the state-of-the-art performance in action recognition, video-text tasks, and video-centric dialogue. Our approach employs a progressive training paradigm that unifies the different self- or weakly-supervised learning frameworks of masked video token reconstruction, cross-modal contrastive learning, and next token prediction. Different training stages would guide our model to capture different levels of structure and semantic information through different pretext tasks. At the data level, we prioritize the spatiotemporal consistency by semantically segmenting videos and generating video-audio-speech captions. This improves the alignment between video and text. We scale both data and model size for our InternVideo2. Through extensive experiments, we validate our designs and demonstrate the state-of-the-art performance on over 60 video and audio tasks. Notably, our model outperforms others on various video-related captioning, dialogue, and long video understanding benchmarks, highlighting its ability to reason and comprehend long temporal contexts. Code and models are available at //github.com/OpenGVLab/InternVideo2/.
We introduce Videoshop, a training-free video editing algorithm for localized semantic edits. Videoshop allows users to use any editing software, including Photoshop and generative inpainting, to modify the first frame; it automatically propagates those changes, with semantic, spatial, and temporally consistent motion, to the remaining frames. Unlike existing methods that enable edits only through imprecise textual instructions, Videoshop allows users to add or remove objects, semantically change objects, insert stock photos into videos, etc. with fine-grained control over locations and appearance. We achieve this through image-based video editing by inverting latents with noise extrapolation, from which we generate videos conditioned on the edited image. Videoshop produces higher quality edits against 6 baselines on 2 editing benchmarks using 10 evaluation metrics.
Modern Large Language Models (LLMs) are capable of following long and complex instructions that enable a diverse amount of user tasks. However, despite Information Retrieval (IR) models using LLMs as the backbone of their architectures, nearly all of them still only take queries as input, with no instructions. For the handful of recent models that do take instructions, it's unclear how they use them. We introduce our dataset FollowIR, which contains a rigorous instruction evaluation benchmark as well as a training set for helping IR models learn to better follow real-world instructions. FollowIR builds off the long history of the TREC conferences: as TREC provides human annotators with instructions (also known as narratives) to determine document relevance, so should IR models be able to understand and decide relevance based on these detailed instructions. Our evaluation benchmark starts with three deeply judged TREC collections and alters the annotator instructions, re-annotating relevant documents. Through this process, we can measure how well IR models follow instructions, through a new pairwise evaluation framework. Our results indicate that existing retrieval models fail to correctly use instructions, using them for basic keywords and struggling to understand long-form information. However, we show that it is possible for IR models to learn to follow complex instructions: our new FollowIR-7B model has significant improvements (over 13%) after fine-tuning on our training set.
With the burgeoning growth of online video platforms and the escalating volume of video content, the demand for proficient video understanding tools has intensified markedly. With Large Language Models (LLMs) showcasing remarkable capabilities in key language tasks, this survey provides a detailed overview of the recent advancements in video understanding harnessing the power of LLMs (Vid-LLMs). The emergent capabilities of Vid-LLMs are surprisingly advanced, particularly their ability for open-ended spatial-temporal reasoning combined with commonsense knowledge, suggesting a promising path for future video understanding. We examine the unique characteristics and capabilities of Vid-LLMs, categorizing the approaches into four main types: LLM-based Video Agents, Vid-LLMs Pretraining, Vid-LLMs Instruction Tuning, and Hybrid Methods. Furthermore, this survey also presents a comprehensive study of the tasks and datasets for Vid-LLMs, along with the methodologies employed for evaluation. Additionally, the survey explores the expansive applications of Vid-LLMs across various domains, thereby showcasing their remarkable scalability and versatility in addressing challenges in real-world video understanding. Finally, the survey summarizes the limitations of existing Vid-LLMs and the directions for future research. For more information, we recommend readers visit the repository at //github.com/yunlong10/Awesome-LLMs-for-Video-Understanding.
Diffusion models (DMs) have shown great potential for high-quality image synthesis. However, when it comes to producing images with complex scenes, how to properly describe both image global structures and object details remains a challenging task. In this paper, we present Frido, a Feature Pyramid Diffusion model performing a multi-scale coarse-to-fine denoising process for image synthesis. Our model decomposes an input image into scale-dependent vector quantized features, followed by a coarse-to-fine gating for producing image output. During the above multi-scale representation learning stage, additional input conditions like text, scene graph, or image layout can be further exploited. Thus, Frido can be also applied for conditional or cross-modality image synthesis. We conduct extensive experiments over various unconditioned and conditional image generation tasks, ranging from text-to-image synthesis, layout-to-image, scene-graph-to-image, to label-to-image. More specifically, we achieved state-of-the-art FID scores on five benchmarks, namely layout-to-image on COCO and OpenImages, scene-graph-to-image on COCO and Visual Genome, and label-to-image on COCO. Code is available at //github.com/davidhalladay/Frido.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191