Conventional Vision Transformer streamlines visual modeling by employing a uniform input resolution, which underestimates the inherent variability of natural visual data and incurs a cost in spatial-contextual fidelity. While preliminary explorations have superficially investigated native resolution modeling, existing works still lack systematic training recipe from the visual representation perspective. To bridge this gap, we introduce Unified Vision Transformer with Native Resolution, i.e. UniViTAR, a family of homogeneous vision foundation models tailored for unified visual modality and native resolution scenario in the era of multimodal. Our framework first conducts architectural upgrades to the vanilla paradigm by integrating multiple advanced components. Building upon these improvements, a progressive training paradigm is introduced, which strategically combines two core mechanisms: (1) resolution curriculum learning, transitioning from fixed-resolution pretraining to native resolution tuning, thereby leveraging ViT’s inherent adaptability to variable-length sequences, and (2) visual modality adaptation via inter-batch image-video switching, which balances computational efficiency with enhanced temporal reasoning. In parallel, a hybrid training framework further synergizes sigmoid-based contrastive loss with feature distillation from a frozen teacher model, thereby accelerating early-stage convergence. Finally, trained exclusively on public accessible image-caption data, our UniViTAR family across multiple model scales from 0.3B to 1B achieves state-of-the-art performance on a wide variety of visual-related tasks. The code and models are available here.

Recently, feature-based methods for Online Action Detection (OAD) have been gaining traction. However, these methods are constrained by their fixed backbone design, which fails to leverage the potential benefits of a trainable backbone. This paper introduces an end-to-end learning network that revises these approaches, incorporating a backbone network design that improves effectiveness and efficiency. Our proposed model utilizes a shared initial spatial model for all frames and maintains an extended sequence cache, which enables low-cost inference. We promote an asymmetric spatiotemporal model that caters to long-form and short-form modeling. Additionally, we propose an innovative and efficient inference mechanism that accelerates extensive spatiotemporal exploration. Through comprehensive ablation studies and experiments, we validate the performance and efficiency of our proposed method. Remarkably, we achieve an end-to-end learning OAD of 17.3 (+12.6) FPS with 72.4% (+1.2%), 90.3% (+0.7%), and 48.1% (+26.0%) mAP on THMOUS’14, TVSeries, and HDD, respectively. The source code is available at https://github.com/sqiangcao99/E2E-LOAD.

In this paper, we propose a novel method to mine the commonsense knowledge shared between the video and text modalities for video-text retrieval, namely visual consensus modeling. Different from the existing works, which learn the video and text representations and their complicated relationships solely based on the pairwise video-text data, we make the first attempt to model the visual consensus by mining the visual concepts from videos and exploiting their co-occurrence patterns within the video and text modalities with no reliance on any additional concept annotations. Specifically, we build a shareable and learnable graph as the visual consensus, where the nodes denoting the mined visual concepts and the edges connecting the nodes representing the co-occurrence relationships between the visual concepts. Extensive experimental results on the public benchmark datasets demonstrate that our proposed method, with the ability to effectively model the visual consensus, achieves state-of-the-art performances on the bidirectional video-text retrieval task. Our code is available at https://github.com/sqiangcao99/VCM.

In this paper, the problem of describing visual contents of a video sequence with natural language is addressed. Unlike previous video captioning work mainly exploiting the cues of video contents to make a language description, we propose a reconstruction network (RecNet) in a novel encoder-decoder-reconstructor architecture, which leverages both forward (video to sentence) and backward (sentence to video) flows for video captioning. Specifically, the encoder-decoder component makes use of the forward flow to produce a sentence based on the encoded video semantic features. Two types of reconstructors are subsequently proposed to employ the backward flow and reproduce the video features from local and global perspectives, respectively, capitalizing on the hidden state sequence generated by the decoder. Moreover, in order to make a comprehensive reconstruction of the video features, we propose to fuse the two types of reconstructors together. The generation loss yielded by the encoder-decoder component and the reconstruction loss introduced by the reconstructor are jointly cast into training the proposed RecNet in an end-to-end fashion. Furthermore, the RecNet is fine-tuned by CIDEr optimization via reinforcement learning, which significantly boosts the captioning performance. Experimental results on benchmark datasets demonstrate that the proposed reconstructor can boost the performance of video captioning consistently.

In this paper, we propose a novel model with a hierarchical photo-scene encoder and a reconstructor for the task of album storytelling. The photo-scene encoder contains two subencoders, namely the photo and scene encoders, which are stacked together and behave hierarchically to fully exploit the structure information of the photos within an album. Specifically, the photo encoder generates semantic representation for each photo while exploiting temporal relationships among them. The scene encoder, relying on the obtained photo representations, is responsible for detecting the scene changes and generating scene representations. Subsequently, the decoder dynamically and attentively summarizes the encoded photo and scene representations to generate a sequence of album representations, based on which a story consisting of multiple coherent sentences is generated. In order to fully extract the useful semantic information from an album, a reconstructor is employed to reproduce the summarized album representations based on the hidden states of the decoder. The proposed model can be trained in an end-to-end manner, which results in an improved performance over the state-of-the-arts on the public visual storytelling (VIST) dataset. Ablation studies further demonstrate the effectiveness of the proposed hierarchical photo-scene encoder and reconstructor.

In this paper, we propose to guide the video caption generation with Part-of-Speech (POS) information, based on a gated fusion of multiple representations of input videos. We construct a novel gated fusion network, with one particularly designed cross-gating (CG) block, to effectively encode and fuse different types of representations, e.g., the motion and content features of an input video. One POS sequence generator relies on this fused representation to predict the global syntactic structure, which is thereafter leveraged to guide the video captioning generation and control the syntax of the generated sentence. Specifically, a gating strategy is proposed to dynamically and adaptively incorporate the global syntactic POS information into the decoder for generating each word. Experimental results on two benchmark datasets, namely MSR-VTT and MSVD, demonstrate that the proposed model can well exploit complementary information from multiple representations, resulting in improved performances. Moreover, the generated global POS information can well capture the global syntactic structure of the sentence, and thus be exploited to control the syntactic structure of the description. Such POS information not only boosts the video captioning performance but also improves the diversity of the generated captions. Our code is at: https://github.com/vsislab/Controllable_XGating.

In this paper, the problem of describing visual contents of a video sequence with natural language is addressed. Unlike previous video captioning work mainly exploiting the cues of video contents to make a language description, we propose a reconstruction network (RecNet) with a novel encoder-decoder-reconstructor architecture, which leverages both the forward (video to sentence) and backward (sentence to video) flows for video captioning. Specifically, the encoder-decoder makes use of the forward flow to produce the sentence description based on the encoded video semantic features. Two types of reconstructors are customized to employ the backward flow and reproduce the video features based on the hidden state sequence generated by the decoder. The generation loss yielded by the encoder-decoder and the reconstruction loss introduced by the reconstructor are jointly drawn into training the proposed RecNet in an end-to-end fashion. Experimental results on benchmark datasets demonstrate that the proposed reconstructor can boost the encoder-decoder models and leads to significant gains in video caption accuracy.