Snapshot compressive imaging (SCI) and video compressive sensing (VCS) typically use fixed, globally uniform compression ratios that ignore spatio-temporal heterogeneity. We present D-STCRL, a reinforcement-learned framework that unifies adaptive sensing and semantic transmission under an explicit rate-distortion-energy objective. The pipeline comprises: (i) a Ratio Generation Network predicts per-patch ratio maps via spatio-temporal attention and 3D frequency cues; (ii) a Programmable Sensing Model emulates pixel-wise variable exposure through differentiable binary gating under a global budget; and (iii) a Frequency-Aware Swin decoder with a low-rank prior restores temporally consistent frames. A multi-objective policy gradient couples the ratio policy with reconstruction and JSCC, yielding stable training. On the NFS benchmark, D-STCRL improves PSNR by$2-3 ~\text{dB}$over fixed-ratio SCI at the same sampling budget; under 10 dB AWGN it surpasses a CRL baseline by$0.6-1.0 ~\text{dB}$while reducing transmitted symbols by up to 15 %. These results unify content-adaptive sensing and efficient transmission for next-generation cameras. Our code, configs and reproducible pipelines will be released upon acceptance.

In this paper, we propose a cross-component attention network (CCA-Net) for in-loop filtering to leverage the strengths of both separate and shared models for luma and chroma components while exploit their cross correlation. Fig. 1 shows the overall network. We adopt a structure akin to multi-task learning and introduce a cross-component attention (CCA) module to guide chroma filtering with luma by modeling the correlation as a linear combination of chroma and luma features with adaptive weights. Experimental results demonstrate that the proposed method achieves$\{0.09 \%, 4.03 \%, 3.37 \%\}$bitrate savings for$\{\mathrm{Y}, \mathrm{U}, \mathrm{V}\}$, compared with the shared model while maintaining similar complexity. Compared with the separate models, the proposed method only has$\{0.35 \%, 0.2 \%, 0.59 \%\}$performance loss for$\{\mathrm{Y}, \mathrm{U}, \mathrm{V}\}$, but significantly reduces the computation and parameters by 50 %.